汉语财经评论的修辞结构标注及篇章研究
|
摘要
篇章标注是国际语言资源建设的一个前沿内容。本文遵循国际篇章语料库的建设方法,通过先建立一个较大规模的以语篇为单位的汉语财经评论篇章语料库,然后在修辞结构理论(Rhetorical Structure Theory,RST)的指导下对语料进行了预处理、切分、标注、核查和统计分析,并研究了汉语篇章的修辞结构与表层语言信息之间的各种量化关系,试图为对比语言学和将来建立更大的、自动处理的篇章语料库做些基础工作。
在进行汉语篇章修辞结构树库建设的具体工作之前,我们首先从理论上比较了从英语研究发展出来的RST和汉语相关的传统复句、句群、语篇和文章学研究,认为两者在关于篇章结构的基本假设和很多具体问题的结论上都非常相似,但是RST理论在坚持语言的交际观、强调作者交际意图与篇章单元修辞意义的核心性地位的关联性、强调语言结构层级的同质性,以及篇章修辞结构的形式化表达等方面具有比较突出的特点。因此,在总结了RST汉语研究和国际篇章修辞结构树库的建设成绩之后,我们认为有可能也有必要利用该理论对汉语篇章进行基于语料库的实证研究。
为此,我们建立了一个含400篇,约80万字的汉语财经评论篇章语料库(Caijingpinglun,CJPL)。该语料库在语料选材上与英语WSJ-RST树库和德语的PCC树库有比较好的可类比性。不过由于语料直接取自网页,存在一些字符编码、文字编辑以及网页上传等问题,所以我们采取了各种比较谨慎的预处理步骤,将网页文档全部转换成有统一编码的文本文档,以保证后续处理的精度和效率。
在预处理程序后,标注者首先在文本文档的基础上(同时参考原始网页文档),用普通读者的眼光对全部篇章语料进行了基本信息标注,包括各篇文章的体裁、题材、标题、导语、开头、结尾、出处、作者、来源等,并籍此对语料有了较好的了解。
接着,我们依靠选定的篇章基本分析单元(Elementary Unit of Discourse Analysis,EUDA)边界标示符,由机器统一完成了语料的切分。在选定句号、问号、叹号、段落结束标记、分号、冒号、省略号和破折号等篇章单元边界标示符之前,我们对语料中标点符号的分布进行分析。分析显示这些标点符号不仅在绝大多数情况下正确地标示了篇章单元的边界,而且能够保证后续的关系标注具有较小的颗粒度。更为重要的是,根据这些选定的篇章边界符号完成切分之后,我们不再需要对切分结果进行人工干预,只需对极个别切分结果进行粘合,保证了处理的效率和正确率。
在完成切分之后,标注者试验性地标注了所有文章各篇章单元之间的修辞关系,以至整个篇章的修辞结构树构造,从修辞结构角度对语料有了更进一步的理解。在该阶段结束的时候,我们筛除了2个存在严重编辑问题的文档和3个以口语性对话为主的长篇电视采访记录文档。
从评论语料的实际出发,我们定义了12大组47种汉语的修辞关系和19种新闻篇章组织元素,并拟定了汉语篇章关系标注的工作守则,其中包括可能存在歧义时的修辞关系优先选用原则和一些特殊现象的处理方案。在设立关系和对关系进行定义的时候,我们不仅参考了多个英语、德语、汉语版本的修辞关系集及定义,也参考了汉语复句、句群和语篇研究的相关成果。另外,我们还对一些可能有所争议的切分标记和关系定义进行了一项心理语言学的调查。根据调查结果,又调整了部分关系的定义和关系优先选用顺序。
在上述工作的基础上,我们按随机平均抽样原则选取了197篇语料,分2遍完成了对其中较短的97篇文章在EUDA(相当于分号句)及以上层级的修辞关系标注,为每个篇章建立一个覆盖整个文本的篇章修辞结构树,并执行了树结构有效性核查。根据两个版本的修辞结构标注,我们统一了最后的标注(第3遍),然后进行了随机抽样的标注者一致性测试。
我们还在不参考修辞结构标注结果的情况下,为97篇语料单独标注了句间篇章提示标记(包括句间关联词语、句间回指指示词和回指代词、有篇章作用的标点符号)。
之后,我们利用这些标注结果提取了数据,分析了这些评论语篇各个层级的结构特点、修辞关系的分布和篇章提示语的修辞功能。这项语料库驱动的数据分析显示,
1)遵循一定的原则,汉语财经评论绝大多数(93.1%)都能用树结构作大致的形式化表示;
2)我们所定义的修辞关系基本上都能被反复地用来连接在各个层级的篇章单元,显示出汉语篇章具有较好的结构层级同质性。
3)扩展的经典RST关系集(Mann and Thompson 1988,Mann 2005)在汉语财经评论的篇章单元间关系的覆盖比例为90.4%,余下的关系也基本都可以用已知关系的核心性变异类型来表示。
4)汉语财经评论的总体篇章树形,在CJPL语料库中以后段对第一段展开分说的头并卫结构(14.4%)为最多,其次是后段对第一段展开分说并逐步增加其他意思的头降卫结构(13.4%)、先述后评的中降卫结构(13.4%)和逐步展开最后得出结论的尾升卫结构(11.3%)。
5)在CJPL语料库中,全文总体表示证明和评价的占53.6%,全文总体表示阐述、解释信息的占46.4%。这一数据说明国内新闻界对评论的社区定义与语言学界从理论角度对论证文的定义有一定的区别。
6)虽然财经评论正文中的修辞关系有很多是多核心的,但单核心的核心-卫星模式仍占主导地位,占全部关系总数的64.6%。
7)和汉语复句前偏后正的主导性结构不同,汉语评论文在分号句及以上层次中卫星-核心结构与核心-卫星结构的比例为46.16%:53.84%,核心性和篇章单元的次序之间没有明显的关联。
8)以议论为主的“媒体财经评论”和以消息报道为主的“新闻联播”在各种关系的分布频率上有些差异,显示出语类对于修辞关系分布的影响。
9)汉语评论语篇使用句间关联词语的频率28.5%,其中使用频率最高的连词为“而”;句间关联词语被较多地用于并加-M关系和罗列-M关系;
10)一些关系,如附加-S关系、让步-S/-N关系、罗列-M关系等,常有关联词语标示;而另一些关系,如方式-S关系、引述-S关系、评价-M关系、解答关系-M/-S等,几乎没有关联词语表示。
11)一些常见的关联词语在语料库中都有句内句外的用法,只是分布上有些差异,有些主要在句间(如“然而”),有些主要在句内(如“如果”)。
12)语篇中存在一些句间关联词语连用的现象,大致可以分为强调(或缓和)语气、交叉限制关系和分辖上下文三种类型,其中最后一种类型实际上就是多重复句的关系间包孕能力在句以上单元间的扩展。
13)汉语财经评论文最常用的句间回指指示词是“这”和各种带“这”的词语。
14)一些标点符号,如问号、分号、冒号等,在汉语篇章中有明显的标示篇章单元间修辞关系的作用,而且与修辞关系核心性的关联度很高。
15)虽然一些篇章提示标记(包括关联词语、回指词、标点符号和段落标记等)在汉语篇章中与某些修辞关系有比较强的关联性,但它们之间并不存在一种一一对应的映射关系。
16)利用英、德、西等其他语言RST研究的数据,我们发现,修辞关系的有标频率在很多语种中都比较低,而且都常出现在较低的篇章层级单元之间。一些修辞关系,如让步、条件等有标的比例在各个语种中都比较高,而另一些关系,如评价、背景、详述、解答等的有标比例则都比较低。不过具体的比例和各种标记具体所能限制的关系的类型在各个语种之间略有不同。
17)汉语篇章结构树的局部子树中存在一种比较特殊的螺旋型的结构。这一结构形式中,一个篇章单元总是与一个离其较远的单元发生修辞关系,而不是与其直接邻居发生修辞关系。如果这就是Kaplan(1966)所谓的圆周型(Circular)结构,且如果将来更多的语篇标注结果显示这一局部子树的结构形式有比较显著的频率,那么将说明Kaplan(1966)关于汉语篇章圆周型结构的假设有其正确的一面。
18)汉语篇章修辞结构的层级同质性、汉语篇章结构中核心-卫星模式的主导地位以及经典RST关系集在汉语中的覆盖率都从实证角度说明了RST理论在汉语中的可移用性。
虽然汉语财经评论树库的建设目前只取得了阶段性的进展,但我们认为,这一研究在中文信息处理、篇章理论研究和社会文化研究等方面都具有现实意义。
首先,汉语财经评论树库的构建,可以为自然语言工程界提供篇章剖析所需的各类先验系数,帮助他们改进现有的汉语自动文摘模型,并为现有汉语自动篇章剖析算法提供训练和测试的平台。有了汉语RST树库,也就有了借鉴应用英语、德语等其他语种的篇章处理技术的物质基础,将帮助中文信息处理尽快地缩小与其他语言信息处理的差距。
其次,我们对汉语财经评论语料的标注研究,在较大规模数据的基础上检验了修辞结构理论及其形式化方法在汉语中的可移用性。同时,我们也从篇章修辞结构的角度,拓展了汉语篇章提示标记的研究视野。如果有类比性好的语料库,也可以进行语言对比研究、语类对比研究等。
另外,虽然语料库建设目前还很少用来为人文社会科学提供资源,我们还是可以预见它的广阔用途,比如基于大规模语料库的语用事实挖掘。在语料库基础上对汉语新闻评论做语言学性质的研究也会是一片广阔的天空。
The revival of empirical paradigm and the application of machine learning have made the construction of linguistic resource a crucial task in natural language processing. The improvement in character/word and sentence processing and the ultimate goal of discourse processing have made discourse annotation an international frontier. This dissertation reports my efforts to enrich Chinese language resources through the building of a Chinese news commentary treebank, using the Rhetorical Structure Theory (RST) as its theoretical framework. Following the internationally observed methodology in corpus construction, I first did a pilot study, then on the selected corpus I took necessary steps including pre-processing, segmentation, relation annotation, validity checking and inner-coder agreement test to ensure the quality of the annotated discourses. Driven by the statistics obtained from the finished part of the corpus, I studied various correlations between the rhetorical structure and surface linguistic forms. This study can serve the purpose of providing a priori scores for automatic Chinese text parsers and summarizers, or for quantitative linguistic studies.
Specifically, I did the following work:
Before setting off to the detailed tasks of corpus construction, I did a theoretical analogy on the similarities and disparities between the English-rooted RST and Chinese traditional linguistic studies on Sentence Complexes (Fuju), Sentence Groups (Juqun), Discourse and Literary Composition (Wenzhang Xue). Various evidences show that the two schools have common grounds on the hypotheses on discourse structure and many specific observations, but RST is more consistent in its communicative perspective on language, and thereby lays more emphasis on the tie between writer’s intentions and the nucleus status of discourse units, is more insistent on homogeneity among layers of discourse units, and makes more efforts on formalization. The analogy, together with a review on Chinese RST studies and international RST treebank achievements, proved the plausibility and necessity to do a large-scale, corpus-based analysis on Chinese texts.
For that purpose, I composed a Chinese financial news commentary corpus (Caijingpinglun, CJPL) with 400 news texts of about 780,000 characters. Mainly made up of financial news reports and commentaries, this CJPL corpus is of fair comparability to the English WSJ-RST treebank made up of Wall Street Journal articles, and to the German PCC treebank made up of Maerkische Allegemeine Zeitung commentary articles. Upon finishing the pre-processing steps, I first tagged, as an ordinary reader, basic documentary information to every text in CJPL, including Genre, Topic, Title, Lead, Opening, Ending, Source, Author, Publisher, and so on.
Then I carried out a semi-automatic segmentation procedure based on selected EUDA (Elementary Unit of Discourse Analysis) delimiters, namely Full-stop, Question-mark, Exclamation-mark, End-of-paragraph sign, Semicolon, Colon, Ellipsis and Dash. The selection of these delimiters were based on a corpus study on their distribution, which revealed that they can not only signal the boundaries of discourse units in the majority cases but also effectively help reduce the granularity of later discourse analysis. This segmentation procedure yielded undisputable segments, which only need occasional rebinding but no further hand segmentation.
After segmentation, I did a trial annotation to all the inter-EUDA relations of the 400 texts up to the completion of a discourse tree covering the whole text. By that time I felt to have gained fair understanding of my texts. Then I exclude 2 pieces of questionable integrity and 3 lengthy TV interview transcripts of mainly oral exchanges.
Rooted in the linguistic facts of my corpus, I drafted, together with their corresponding definitions, a Chinese rhetorical relation set of 47 relations. I’ve also drafted an inventory of 19 scheme elements for news texts, and a working manual of how to cope with typical problems in relation tagging. While composing the definitions and the manual, I made constant references to various rhetorical inventories and traditional Chinese studies. Apart from that, I conducted a psycholinguistic study on native speakers’preference for certain structures and relation definitions.
Based on the above-mentioned trial tagging, I annotated 97 shortest documents of 197 randomly selected ones from the 395 qualified corpus texts, following relation definitions and tagging conventions drafted. Each of the 97 documents was annotated twice and, when the whole lot was finished, checked for Tree structure validity. A third-time annotation was done to unify choices made in the first- and second-round of annotation, followed by an inner-coder consistency test and extraction of data for statistic analysis.
Apart from rhetorical annotation, I also tagged inter-EUDA cue phrases (including inter-EUDA connectives and connectors, inter-EUDA deictic anaphora and pronoun anaphora, as well as discursively functioning orthographical marks). The tagging was done without reference to the rhetorical annotation.
Data extracted from the completed portion of CJPL corpus suggest the following points:
1) Following certain principles and conventions, the majority of Chinese news commentaries (93.1%) can be represented by a Tree structure;
2) That the rhetorical relations (RRs) defined can be recursively applied to different layers of Chinese discourse units, demonstrates good homogeneity of Chinese text structure.
3) The Extended relations of the Classic RST set (Mann and Thompson 1988, Mann 2005) cover 90.4% of all the cases in the Chinese Financial News Commentary Corpus, and the rest can be covered by deviations of those known RRs.
4) The most popular overall Tree structure in CJPL is an opening sentence as Nucleus with a Satellite of multi-nuclear relations (14.4%), followed by an opening sentence as Nucleus with a satellite of mono-nucleic nucleus (13.4%), an opening sentence as Satellite with a nucleus of mono-nucleic nucleus (13.4%), and an opening sentence as Satellite with a nucleus of mono-nucleic satellite and a closing nucleus (11.3%).
5) 53.6% of the root relations of the body of Chinese news commentaries are of JUSTIFY, EVALUATION and other presentational relations, suggesting a wide difference between practical definition of Commentary in the Chinese mass media community and the theoretical definition given by linguists.
6) Despite a high percentage (35.4%) of multi-nuclear relations, the hypotactic mononuclear relations still withhold their majority.
7) Quite different from the assumed overwhelming pattern of N-S order within Chinese sentence complexes, there is apparently no such dominant order among and above sentences delimited by our selected markers.
8) The different distribution patterns of RRs in the commentary-dominated CJPL corpus and in a report-dominated Chinese TV news report corpus (Xinwenlianbo, XWLB) suggest the influence of genre on RR distribution.
9) About 28.5% of all inter-EUDA relations are marked with conjunction or connectors in CJPL, with the most frequently used being“而(ER)”, and the most frequently marked relations being CONJUNCTION-M and LIST-M.
10) Some relations, such as CONJUNCTION-M, CONCESSION-M/N/S and LIST-M, are frequently marked with conjunctions; while some other relations, such as MEANS-S, ATTRIBUTION-S, EVALUATION-M/N, INTERPRETAION-N, SOLUTION-M/N, are rarely marked with conjunctions.
11) Some common conjunctions are found to be used both below and above sentence level in CJPL, but with different distribution patterns, some are obviously much more frequently used below sentence level, some much more frequently above sentence level, and some no significant difference below and above sentence level.
12) Some inter-EUDA connectors are found to be used consecutively in CJPL texts, and their functions are mainly of the following three types: mitigating or amplifying modality, restricting each other’s rhetorical potentials, and governing different discursive units.
13) The most frequently used inter-EUDA deictic expressions are“这(ZHE)”and words or phrases started with“这(ZHE)”.
14) Some punctuation marks, such as question-mark, semicolon and colon, have strong correlation with certain RRs and their nuclarity patterns.
15) Despite some strong correlations, there is no one-to-one mapping between discursive cue phrases (connectives, connectors, anaphoric deixis, punctuation marks) and RRs.
16) A characteristic subtree structure of spiral shape has been identified in CJPL trees. In this structure, a discourse unit always relates itself not to its immediate neighbor, but to the most distant unit in the subtree. If this was what Kaplan (1966) meant to be the typical circular Chinese discourse structure, and if more cases are found in longer CJPL texts up to a significant level, we could say Kaplan held at least part of the truth. Although this Chinese RST treebank project has only completed partially, it promises practical values in discourse studies and cultural studies as well as in Chinese information processing:
First of all, it is the first attempt to build an RST-annotated Chinese discourse treebank. Given other layers of linguistic information in the near future, this corpus can be used for the extraction of necessary a priori scores needed in Chinese summarizers and be used as a platform for training and testing statistics-based discourse parsers. Therefore, this Chinese RST treebank will serve as an ideal testbed for Chinese computer scientists to catch up with their international competitors in discourse processing.
Secondly, our annotation efforts have proved on a fairly large scale the cross-language transferability of RST and its formalization. Meanwhile, new territories for studies on Chinese cue phrases are also explored. Exciting findings can be expected in Chinese discourse studies after the completion of this treebank. And given some comparable corpora in other languages or other genres, this corpus could also be used as an empirical database for contrastive rhetorical studies.
Finally, we can also predict the usage of annotated Chinese discourse corpus in social sciences, corpus-driven studies on journalism or pragmatics, for instance.
在进行汉语篇章修辞结构树库建设的具体工作之前,我们首先从理论上比较了从英语研究发展出来的RST和汉语相关的传统复句、句群、语篇和文章学研究,认为两者在关于篇章结构的基本假设和很多具体问题的结论上都非常相似,但是RST理论在坚持语言的交际观、强调作者交际意图与篇章单元修辞意义的核心性地位的关联性、强调语言结构层级的同质性,以及篇章修辞结构的形式化表达等方面具有比较突出的特点。因此,在总结了RST汉语研究和国际篇章修辞结构树库的建设成绩之后,我们认为有可能也有必要利用该理论对汉语篇章进行基于语料库的实证研究。
为此,我们建立了一个含400篇,约80万字的汉语财经评论篇章语料库(Caijingpinglun,CJPL)。该语料库在语料选材上与英语WSJ-RST树库和德语的PCC树库有比较好的可类比性。不过由于语料直接取自网页,存在一些字符编码、文字编辑以及网页上传等问题,所以我们采取了各种比较谨慎的预处理步骤,将网页文档全部转换成有统一编码的文本文档,以保证后续处理的精度和效率。
在预处理程序后,标注者首先在文本文档的基础上(同时参考原始网页文档),用普通读者的眼光对全部篇章语料进行了基本信息标注,包括各篇文章的体裁、题材、标题、导语、开头、结尾、出处、作者、来源等,并籍此对语料有了较好的了解。
接着,我们依靠选定的篇章基本分析单元(Elementary Unit of Discourse Analysis,EUDA)边界标示符,由机器统一完成了语料的切分。在选定句号、问号、叹号、段落结束标记、分号、冒号、省略号和破折号等篇章单元边界标示符之前,我们对语料中标点符号的分布进行分析。分析显示这些标点符号不仅在绝大多数情况下正确地标示了篇章单元的边界,而且能够保证后续的关系标注具有较小的颗粒度。更为重要的是,根据这些选定的篇章边界符号完成切分之后,我们不再需要对切分结果进行人工干预,只需对极个别切分结果进行粘合,保证了处理的效率和正确率。
在完成切分之后,标注者试验性地标注了所有文章各篇章单元之间的修辞关系,以至整个篇章的修辞结构树构造,从修辞结构角度对语料有了更进一步的理解。在该阶段结束的时候,我们筛除了2个存在严重编辑问题的文档和3个以口语性对话为主的长篇电视采访记录文档。
从评论语料的实际出发,我们定义了12大组47种汉语的修辞关系和19种新闻篇章组织元素,并拟定了汉语篇章关系标注的工作守则,其中包括可能存在歧义时的修辞关系优先选用原则和一些特殊现象的处理方案。在设立关系和对关系进行定义的时候,我们不仅参考了多个英语、德语、汉语版本的修辞关系集及定义,也参考了汉语复句、句群和语篇研究的相关成果。另外,我们还对一些可能有所争议的切分标记和关系定义进行了一项心理语言学的调查。根据调查结果,又调整了部分关系的定义和关系优先选用顺序。
在上述工作的基础上,我们按随机平均抽样原则选取了197篇语料,分2遍完成了对其中较短的97篇文章在EUDA(相当于分号句)及以上层级的修辞关系标注,为每个篇章建立一个覆盖整个文本的篇章修辞结构树,并执行了树结构有效性核查。根据两个版本的修辞结构标注,我们统一了最后的标注(第3遍),然后进行了随机抽样的标注者一致性测试。
我们还在不参考修辞结构标注结果的情况下,为97篇语料单独标注了句间篇章提示标记(包括句间关联词语、句间回指指示词和回指代词、有篇章作用的标点符号)。
之后,我们利用这些标注结果提取了数据,分析了这些评论语篇各个层级的结构特点、修辞关系的分布和篇章提示语的修辞功能。这项语料库驱动的数据分析显示,
1)遵循一定的原则,汉语财经评论绝大多数(93.1%)都能用树结构作大致的形式化表示;
2)我们所定义的修辞关系基本上都能被反复地用来连接在各个层级的篇章单元,显示出汉语篇章具有较好的结构层级同质性。
3)扩展的经典RST关系集(Mann and Thompson 1988,Mann 2005)在汉语财经评论的篇章单元间关系的覆盖比例为90.4%,余下的关系也基本都可以用已知关系的核心性变异类型来表示。
4)汉语财经评论的总体篇章树形,在CJPL语料库中以后段对第一段展开分说的头并卫结构(14.4%)为最多,其次是后段对第一段展开分说并逐步增加其他意思的头降卫结构(13.4%)、先述后评的中降卫结构(13.4%)和逐步展开最后得出结论的尾升卫结构(11.3%)。
5)在CJPL语料库中,全文总体表示证明和评价的占53.6%,全文总体表示阐述、解释信息的占46.4%。这一数据说明国内新闻界对评论的社区定义与语言学界从理论角度对论证文的定义有一定的区别。
6)虽然财经评论正文中的修辞关系有很多是多核心的,但单核心的核心-卫星模式仍占主导地位,占全部关系总数的64.6%。
7)和汉语复句前偏后正的主导性结构不同,汉语评论文在分号句及以上层次中卫星-核心结构与核心-卫星结构的比例为46.16%:53.84%,核心性和篇章单元的次序之间没有明显的关联。
8)以议论为主的“媒体财经评论”和以消息报道为主的“新闻联播”在各种关系的分布频率上有些差异,显示出语类对于修辞关系分布的影响。
9)汉语评论语篇使用句间关联词语的频率28.5%,其中使用频率最高的连词为“而”;句间关联词语被较多地用于并加-M关系和罗列-M关系;
10)一些关系,如附加-S关系、让步-S/-N关系、罗列-M关系等,常有关联词语标示;而另一些关系,如方式-S关系、引述-S关系、评价-M关系、解答关系-M/-S等,几乎没有关联词语表示。
11)一些常见的关联词语在语料库中都有句内句外的用法,只是分布上有些差异,有些主要在句间(如“然而”),有些主要在句内(如“如果”)。
12)语篇中存在一些句间关联词语连用的现象,大致可以分为强调(或缓和)语气、交叉限制关系和分辖上下文三种类型,其中最后一种类型实际上就是多重复句的关系间包孕能力在句以上单元间的扩展。
13)汉语财经评论文最常用的句间回指指示词是“这”和各种带“这”的词语。
14)一些标点符号,如问号、分号、冒号等,在汉语篇章中有明显的标示篇章单元间修辞关系的作用,而且与修辞关系核心性的关联度很高。
15)虽然一些篇章提示标记(包括关联词语、回指词、标点符号和段落标记等)在汉语篇章中与某些修辞关系有比较强的关联性,但它们之间并不存在一种一一对应的映射关系。
16)利用英、德、西等其他语言RST研究的数据,我们发现,修辞关系的有标频率在很多语种中都比较低,而且都常出现在较低的篇章层级单元之间。一些修辞关系,如让步、条件等有标的比例在各个语种中都比较高,而另一些关系,如评价、背景、详述、解答等的有标比例则都比较低。不过具体的比例和各种标记具体所能限制的关系的类型在各个语种之间略有不同。
17)汉语篇章结构树的局部子树中存在一种比较特殊的螺旋型的结构。这一结构形式中,一个篇章单元总是与一个离其较远的单元发生修辞关系,而不是与其直接邻居发生修辞关系。如果这就是Kaplan(1966)所谓的圆周型(Circular)结构,且如果将来更多的语篇标注结果显示这一局部子树的结构形式有比较显著的频率,那么将说明Kaplan(1966)关于汉语篇章圆周型结构的假设有其正确的一面。
18)汉语篇章修辞结构的层级同质性、汉语篇章结构中核心-卫星模式的主导地位以及经典RST关系集在汉语中的覆盖率都从实证角度说明了RST理论在汉语中的可移用性。
虽然汉语财经评论树库的建设目前只取得了阶段性的进展,但我们认为,这一研究在中文信息处理、篇章理论研究和社会文化研究等方面都具有现实意义。
首先,汉语财经评论树库的构建,可以为自然语言工程界提供篇章剖析所需的各类先验系数,帮助他们改进现有的汉语自动文摘模型,并为现有汉语自动篇章剖析算法提供训练和测试的平台。有了汉语RST树库,也就有了借鉴应用英语、德语等其他语种的篇章处理技术的物质基础,将帮助中文信息处理尽快地缩小与其他语言信息处理的差距。
其次,我们对汉语财经评论语料的标注研究,在较大规模数据的基础上检验了修辞结构理论及其形式化方法在汉语中的可移用性。同时,我们也从篇章修辞结构的角度,拓展了汉语篇章提示标记的研究视野。如果有类比性好的语料库,也可以进行语言对比研究、语类对比研究等。
另外,虽然语料库建设目前还很少用来为人文社会科学提供资源,我们还是可以预见它的广阔用途,比如基于大规模语料库的语用事实挖掘。在语料库基础上对汉语新闻评论做语言学性质的研究也会是一片广阔的天空。
The revival of empirical paradigm and the application of machine learning have made the construction of linguistic resource a crucial task in natural language processing. The improvement in character/word and sentence processing and the ultimate goal of discourse processing have made discourse annotation an international frontier. This dissertation reports my efforts to enrich Chinese language resources through the building of a Chinese news commentary treebank, using the Rhetorical Structure Theory (RST) as its theoretical framework. Following the internationally observed methodology in corpus construction, I first did a pilot study, then on the selected corpus I took necessary steps including pre-processing, segmentation, relation annotation, validity checking and inner-coder agreement test to ensure the quality of the annotated discourses. Driven by the statistics obtained from the finished part of the corpus, I studied various correlations between the rhetorical structure and surface linguistic forms. This study can serve the purpose of providing a priori scores for automatic Chinese text parsers and summarizers, or for quantitative linguistic studies.
Specifically, I did the following work:
Before setting off to the detailed tasks of corpus construction, I did a theoretical analogy on the similarities and disparities between the English-rooted RST and Chinese traditional linguistic studies on Sentence Complexes (Fuju), Sentence Groups (Juqun), Discourse and Literary Composition (Wenzhang Xue). Various evidences show that the two schools have common grounds on the hypotheses on discourse structure and many specific observations, but RST is more consistent in its communicative perspective on language, and thereby lays more emphasis on the tie between writer’s intentions and the nucleus status of discourse units, is more insistent on homogeneity among layers of discourse units, and makes more efforts on formalization. The analogy, together with a review on Chinese RST studies and international RST treebank achievements, proved the plausibility and necessity to do a large-scale, corpus-based analysis on Chinese texts.
For that purpose, I composed a Chinese financial news commentary corpus (Caijingpinglun, CJPL) with 400 news texts of about 780,000 characters. Mainly made up of financial news reports and commentaries, this CJPL corpus is of fair comparability to the English WSJ-RST treebank made up of Wall Street Journal articles, and to the German PCC treebank made up of Maerkische Allegemeine Zeitung commentary articles. Upon finishing the pre-processing steps, I first tagged, as an ordinary reader, basic documentary information to every text in CJPL, including Genre, Topic, Title, Lead, Opening, Ending, Source, Author, Publisher, and so on.
Then I carried out a semi-automatic segmentation procedure based on selected EUDA (Elementary Unit of Discourse Analysis) delimiters, namely Full-stop, Question-mark, Exclamation-mark, End-of-paragraph sign, Semicolon, Colon, Ellipsis and Dash. The selection of these delimiters were based on a corpus study on their distribution, which revealed that they can not only signal the boundaries of discourse units in the majority cases but also effectively help reduce the granularity of later discourse analysis. This segmentation procedure yielded undisputable segments, which only need occasional rebinding but no further hand segmentation.
After segmentation, I did a trial annotation to all the inter-EUDA relations of the 400 texts up to the completion of a discourse tree covering the whole text. By that time I felt to have gained fair understanding of my texts. Then I exclude 2 pieces of questionable integrity and 3 lengthy TV interview transcripts of mainly oral exchanges.
Rooted in the linguistic facts of my corpus, I drafted, together with their corresponding definitions, a Chinese rhetorical relation set of 47 relations. I’ve also drafted an inventory of 19 scheme elements for news texts, and a working manual of how to cope with typical problems in relation tagging. While composing the definitions and the manual, I made constant references to various rhetorical inventories and traditional Chinese studies. Apart from that, I conducted a psycholinguistic study on native speakers’preference for certain structures and relation definitions.
Based on the above-mentioned trial tagging, I annotated 97 shortest documents of 197 randomly selected ones from the 395 qualified corpus texts, following relation definitions and tagging conventions drafted. Each of the 97 documents was annotated twice and, when the whole lot was finished, checked for Tree structure validity. A third-time annotation was done to unify choices made in the first- and second-round of annotation, followed by an inner-coder consistency test and extraction of data for statistic analysis.
Apart from rhetorical annotation, I also tagged inter-EUDA cue phrases (including inter-EUDA connectives and connectors, inter-EUDA deictic anaphora and pronoun anaphora, as well as discursively functioning orthographical marks). The tagging was done without reference to the rhetorical annotation.
Data extracted from the completed portion of CJPL corpus suggest the following points:
1) Following certain principles and conventions, the majority of Chinese news commentaries (93.1%) can be represented by a Tree structure;
2) That the rhetorical relations (RRs) defined can be recursively applied to different layers of Chinese discourse units, demonstrates good homogeneity of Chinese text structure.
3) The Extended relations of the Classic RST set (Mann and Thompson 1988, Mann 2005) cover 90.4% of all the cases in the Chinese Financial News Commentary Corpus, and the rest can be covered by deviations of those known RRs.
4) The most popular overall Tree structure in CJPL is an opening sentence as Nucleus with a Satellite of multi-nuclear relations (14.4%), followed by an opening sentence as Nucleus with a satellite of mono-nucleic nucleus (13.4%), an opening sentence as Satellite with a nucleus of mono-nucleic nucleus (13.4%), and an opening sentence as Satellite with a nucleus of mono-nucleic satellite and a closing nucleus (11.3%).
5) 53.6% of the root relations of the body of Chinese news commentaries are of JUSTIFY, EVALUATION and other presentational relations, suggesting a wide difference between practical definition of Commentary in the Chinese mass media community and the theoretical definition given by linguists.
6) Despite a high percentage (35.4%) of multi-nuclear relations, the hypotactic mononuclear relations still withhold their majority.
7) Quite different from the assumed overwhelming pattern of N-S order within Chinese sentence complexes, there is apparently no such dominant order among and above sentences delimited by our selected markers.
8) The different distribution patterns of RRs in the commentary-dominated CJPL corpus and in a report-dominated Chinese TV news report corpus (Xinwenlianbo, XWLB) suggest the influence of genre on RR distribution.
9) About 28.5% of all inter-EUDA relations are marked with conjunction or connectors in CJPL, with the most frequently used being“而(ER)”, and the most frequently marked relations being CONJUNCTION-M and LIST-M.
10) Some relations, such as CONJUNCTION-M, CONCESSION-M/N/S and LIST-M, are frequently marked with conjunctions; while some other relations, such as MEANS-S, ATTRIBUTION-S, EVALUATION-M/N, INTERPRETAION-N, SOLUTION-M/N, are rarely marked with conjunctions.
11) Some common conjunctions are found to be used both below and above sentence level in CJPL, but with different distribution patterns, some are obviously much more frequently used below sentence level, some much more frequently above sentence level, and some no significant difference below and above sentence level.
12) Some inter-EUDA connectors are found to be used consecutively in CJPL texts, and their functions are mainly of the following three types: mitigating or amplifying modality, restricting each other’s rhetorical potentials, and governing different discursive units.
13) The most frequently used inter-EUDA deictic expressions are“这(ZHE)”and words or phrases started with“这(ZHE)”.
14) Some punctuation marks, such as question-mark, semicolon and colon, have strong correlation with certain RRs and their nuclarity patterns.
15) Despite some strong correlations, there is no one-to-one mapping between discursive cue phrases (connectives, connectors, anaphoric deixis, punctuation marks) and RRs.
16) A characteristic subtree structure of spiral shape has been identified in CJPL trees. In this structure, a discourse unit always relates itself not to its immediate neighbor, but to the most distant unit in the subtree. If this was what Kaplan (1966) meant to be the typical circular Chinese discourse structure, and if more cases are found in longer CJPL texts up to a significant level, we could say Kaplan held at least part of the truth. Although this Chinese RST treebank project has only completed partially, it promises practical values in discourse studies and cultural studies as well as in Chinese information processing:
First of all, it is the first attempt to build an RST-annotated Chinese discourse treebank. Given other layers of linguistic information in the near future, this corpus can be used for the extraction of necessary a priori scores needed in Chinese summarizers and be used as a platform for training and testing statistics-based discourse parsers. Therefore, this Chinese RST treebank will serve as an ideal testbed for Chinese computer scientists to catch up with their international competitors in discourse processing.
Secondly, our annotation efforts have proved on a fairly large scale the cross-language transferability of RST and its formalization. Meanwhile, new territories for studies on Chinese cue phrases are also explored. Exciting findings can be expected in Chinese discourse studies after the completion of this treebank. And given some comparable corpora in other languages or other genres, this corpus could also be used as an empirical database for contrastive rhetorical studies.
Finally, we can also predict the usage of annotated Chinese discourse corpus in social sciences, corpus-driven studies on journalism or pragmatics, for instance.
引文
2 http://www.cis.upenn.edu/~chinese
7 该网站原来的网址为www.sil.org/~mannb/rst。在Bill Mann于2004年8月13日过世之后,由Maite Taboada负责维护,并迁址到http://www.sfu.ca/rst。
29 Songren Cui. 1986. A Comparison of English and Chinese Expository Rhetorical Structures. UCLA Master thesis.
30 R. R. Kaplan. 1966. Cultural Thought Patterns in Intercultural Communication. Language Learning. 16:1-20.
36 张志公,1962,《谈词章之学》,转引自王福祥(1989:8)。
37 张寿康,1983,‘试论文章学研究’,《汉语论丛》,转引自王福祥(1989:9)。
40 吕叔湘.《汉语语法分析问题》. 1979.商务印书馆.收录在《汉语语法论文集(增订本)》.商务印书馆. 1984. pp481-571.
41 廖秋忠(1992:120-30)“篇章中的论证结构”,原载于《语言教学与研究》1998 年第 1 期。
43 廖秋忠,“篇章与语用和句法研究”,原载于《语言教学与研究》1991 年第四期。《廖秋忠文集》(1992)转载,具体语句见第 203 页注⒁。
50 引用王一禾(2001):“符号小,学问大——写在《标点符号学习与应用》重印之际”。转载于http://www.epsalon.com/printpage.asp?ArticleID=957
[Allen,1994] James Allen. Natural Language Understanding.The Benjamin/Cummings Publishing Company. 1994.
[Bateman and Delin, 2005] John Bateman and Judy Delin. Rhetorical structure theory. In Encyclopedia of Language and Linguistics (2nd ed.). Oxford: Elsevier. 2005.
[Bateman and Rondhuis, 1997] John Bateman and K. J. Rondhuis. "Coherence relations": Toward a General Specification. Discourse Processes. 24(1): 5-50. 1997.
[Bateman et al., 2001]John Bateman, Thomas Kamps, J?rg Kleinz and Klaus Reichenberger. Towards constructive text, diagram, and layout generation for information presentation. Computational Linguistics, 2001. 27 (3), 409-449.
[Berger et al., 2002] Daniela Berger, David Reitter and Manfred Stede. XML/XSL in the Dictionary: The Case of Discourse Markers. In Proceedings of the COLING Workshop NLPXML-2002. Taipei.
[Bloomfield,1933(2002)] Leonard Bloomfield. 1933. Language. Reprinted by Foreign Language Teaching and Research Press. Beijing. 2002.
[Burstein and Marcu, 2003] J. Burstein, and Daniel Marcu. A machine learning approach for identification of thesis and conclusion statements in student essays. Computers and the Humanities. 37(4), 455-467. 2003.
[Carlson and Marcu, 2002] Lynn Carlson and Daniel Marcu. Discourse Tagging Manual. http://www.isi.edu/~marcu/discourse/tagging-ref-manual.pdf. 2002.
[Carlson et al., 2001] Carlson, Lynn, John Conroy, Daniel Marcu, Dianne O'Leary, Mary Ellen Okurowski, Anthony Taylor and William Wong. An empirical study of the relation between abstracts, extracts, and the discourse structure of texts, Proceedings of Document Understanding Conference (DUC-2001). New Orleans, Louisiana. 2001.
[Carlson et al., 2003] Lynn Carlson, Daniel Marcu, and Mary E. Okurowski. Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. In Jan van Kuppevelt and Ronnie Smith, editors, Current Directions in Discourse and Dialogue. Kluwer Academic Publishers. 2003.
[Chalker, 2000] Sylvia Chalker. Linking Words (《连词》,刘万存译). HK: Commercial Press. 2000.
[Chan et al., 2000] Samuel W. K. Chan, Tom B. Y. Lai, W. J. Gao and Benjamin K. T’sou. Mining discourse markers for Chinese Textual Summarization. Workshop on Automatic Summarization, ACL 2000.
[Chu, 1998] Chauncey C. Chu(屈承熹). A Discourse Grammar of Mandarin Chinese. Peter Lang Publishing. N.Y. 1998.
[Connor, 2002] Ulla Connor. New directions in contrastive rhetoric. Tesol Quarterly, 36 (4), 493-510. 2002.
[Corston-Oliver, 1998] Simon H. Corston-Oliver. Computing Representation of the Structure of Written Discourse. Technical Report, MSR-TR-98-15. 1998.
[Cristea and Webber, 1997] Dan Cristea and Bonnie Webber. Expectations in incremental discourse processing. Proceedings of 35th Annual Meeting of the Association for Computational Linguistics (ACL'97). Vol.1, pp.88-95. Madrid, Spain. 1997.
[Cristea et al., 2000] Cristea, Dan, Nancy Ide and Laurent Romary. Veins Theory: A model of global discourse cohesion and coherence, Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (ACL-98/COLING-98). pp. 281-285. Montréal, Canada. 1998.
[Cristea et al., 2000] Dan Cristea , Nancy Ide, Daniel Marcu and Valentin Tablan. Discourse structure and coreference: An empirical study. In Proceedings of the 18th International Conference on Computational Linguistics (COLING'00) (Vol. 1, pp. 208-214). Saarbrüken, Germany. 2000.
[Cui,1986] Songren Cui. A Comparison of English and Chinese Expository Rhetorical Structures. MA diploma thesis, UCLA. 1986.
[Dale, 1991] Robert Dale. The role of punctuation in discourse structure. Proceedings of AAAI Fall Symposium on Discourse Structure in Natural Language Understanding and Generation (pp. 13-14). Asilomar, CA. 1991.
[den Ouden, 2004] Hanny den Ouden. Prosodic Realizations of Text Structure. Ph.D. dissertation, University of Tilburg, Tilburg, The Netherlands. 2004.
[van Dijk, 1979] Teun A.van Dijk. Pragmatic connectives. Journal of Pragmatics, Vol.(3): 447-456. 1979.
[van Dijk, 1980] Teun A. van Dijk. Macrostructures: An Interdisciplinary Study of Global Structures. in Discourse Interaction and Cognition. 1980. Hillsdale, NJ: Lawrence Erlbaum.
[Fawcett an Davies, 1992] Robin P. Fawcett and Bethan L. Davies. Monologue as a turn in dialogue: Towards an integration of Exchange Structure and Rhetorical Structure Theory. In R. Dale, E. Hovy,D. R?sner and O. Stock (Eds.), Aspects of Automated Language Generation (pp. 151-166). Berlin: Springer. 1992.
[Fox, 1987] Barbara A. Fox. 1987. Discourse Structure and Anaphora: Written and Conversational English. Cambridge: Cambridge University Press.
[Fraser, 1999] Bruce Fraser. 1999. What are discourse markers? Journal of Pragmatics 31: 931-952.
[Gaddy et al., 2001] The influence of text cues on the allocation during reading. In Sanders et al. (2003).pp89-110.
[Gaizauskas et al., 2003] Rob Gaizauskas, Patrick Hans,James Pustejovsky, Roser Sauri, Andrew See, Andrea Setzer, Liser Ferro, and Beth Sundheim. The Timebank corpus. In Corpus Linguistics 2003. Lancaster. 2003.
[Germann et al., 2003]Ulrich Germann, Mike Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada. Fast Decoding and Optimal Decoding for Machine Translation. Artificial intelligence, 2003. 154 (1-2), pp. 127-143.
[Gil and Ratnakar, 2002] Gil, Y. and V. Ratnakar. TRELLIS: An interactive tool for capturing information analysis and decision making. In Knowledge Engineering and Knowledge Management,Proceedings. 2002. pp. 37-42.
[Grimes, 1975] J. E. Grimes. The Thread of Discourse. The Hague: Moulton Press. 1975.
[Grosz and Sidner, 1986] Barbara J.Grosz and C. L.Sidner. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3), 175-204. 1986.
[Halliday and Hasan, 1976] M.A.K. Halliday and Ruqaiya Hasan. 1976. Cohesion in English. London: Longman. Reprinted by Foreign Languages and Teaching Press. Beijing. 2000.
[Halliday, 1981] M.A.K. Halliday. Text Semantics and Clause Grammar: How is a Text Like a Clause ?. in Sture Allen (ed.) :Text Processing : Text Analysis and Generation, Text Typology and Attention (Proceedings of Nobel Symposium 51). Stockholm : Almqvist and Wiksell. 209-47. 1982.
[Halliday, 1985/1994] M.A.K. Halliday. An Introduction to Functional Grammar. Edward Arnold, London. 1985/1994.
[Hosti, 1969] O. R. Holsti. Content analysis for the social sciences and humanities. Reading, MA: Addison-Wesley Publishing Co. 1969.
[Hovy and Maier, 1992] Eduard Hovy and E. Maier. Parsimonious of Profligate: How Many and Which Discourse Structure Relations?. Technical Report ISI/RR-93-373. Information Sciences Institute, CA. 1992.
[Hovy, 1988] Eduard Hovy. Planning coherent multisentential text. Proceedings of 26th Annual Meeting of the Association for Computational Linguistics (ACL'88). pp. 163-169. Buffalo, New York. 1988.
[Hovy, 1990] Eduard Hovy. Parsimonious and profligate approaches to the question of discourse structure relations. 5th International Workshop on Text Generation (pp. 59-65). Pittsburgh, PA. 1990.
[Hovy, 1991] Eduard Hovy. Recent trends in computational research on monologic discourse structure. Computational Intelligence. 1991. Vol.7, pp.363-366.
[Hovy, 1993] Eduard Hovy. From interclausal relations to discourse structure- A long way behind, a long way ahead. In H. Horacek & M. Zock (Eds.), 1993. New Concepts in Natural Language Generation (pp. 57-68). London: Pinter.
[Itule and Anderson, 2003] Bruce Itule and Douglas A. Anderson. News Writing and Reporting for Today’s Media. (6th Ed.). McGraw-Hill/中国人民大学出版社. 2003.
[Jones, 1996] Bernard Jones. What’s The Point? A (Computational) Theory of Punctuation. Phd thesis. 1996.
[Kight and Marcu, 2005] Kevin Knight and Daniel Marcu. Machine Translation in Year 2004. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005. Philadelphia, PA.
[Knott and Dale, 1994] Alistair Knott and Robert Dale. Using Linguistic Phenomena to Motivate a Set of Coherence Relations. Discourse Processes. 1994. 18: 35-62.
[Knott and Sanders, 1998] Alistair Knott and T. Sanders. The classification of coherence relations and their linguistic markers: An exploration of two languages. Journal of Pragmatics. 1998. 30(2): 135-175.
[Knott et al., 2001] Alistair Knott, Jon Oberlander, Michael O'Donnell and Chris Mellish. Beyond elaboration: The interaction of relations and focus in coherent text. In T. Sanders, J. Schilperoord and W. Spooren (Eds.), Text Representation: Linguistic and Psycholinguistic Aspects. 2001. pp. 181-196. Amsterdam and Philadelphia: John Benjamins.
[Knott, 1996] Alistair Knott. A Data-Driven Methodology for Motivating a Set of Coherence Relations. Unpublished Ph.D. dissertation, University of Edinburgh, Edinburgh, UK. 1996.
[Knott, 1998] Alistair Knott. Similarity and contrast relations and inductive rules, Proceedings of ACL Workshop on Discourse Relations and Discourse Markers (pp. 54-57). Montréal, Canada. 1998.
[Kong, 1998] K.C.C. Kong. Are simple business request letters really simple? A comparison of Chinese and English business request letters. Text. Vol.18(1): 103-41. 1998.
[Le and Abeysinghe, 2003] H. T. Le and G.Abeysinghe. A Study to Improve the Efficiency of a Discourse Parsing System. CICLing 2003.
[Lindley et al., 2001] Craig Lindley, Jim Davis, Frank Nack, and Lloyd Rutledge. The application of rhetorical structure theory to interactive news program generation from digital archives. Technical Report INS-R0101, CWI Centrum voor Wiskunde en Informatica, January 2001.
[Longacre, 1983] R. E.Longacre. The Grammar of Discourse. New York: Plenum. 1983.
[Maier and Hovy, 1991] Elisabeth Maier and Eduard Hovy. A metafunctionally motivated taxonomy for discourse structure relations, Proceedings of 3rd European Workshop on Language Generation. 1991.Innsbruck, Austria.
[Mann and Thompson, 1983] William Mann, and Sandra Thompson. Relational Propositions in Discourse. Information Sciences Institute of University of Southern California, Los Angeles, ISI/RR-83-115, 1-28. 1983.
[Mann and Thompson, 1987a] William Mann, and Sandra Thompson. Rhetorical Structure Theory: A Theory of Text Organization: ISI/RS-87-190. Information Sciences Institute, University of Southern California. 1987.
[Mann and Thompson, 1987b] William Mann, and Sandra Thompson. Rhetorical Structure Theory: A Framework for the Analysis of Texts." IPRA Papers in Pragmatics 1: 1-21. 1987."
[Mann and Thompson, 1988] William Mann, and Sandra Thompson. Rhetorical Structure Theory: Toward a functional theory of text organization. Text. 8(3):243-281. 1988.
[Mann and Thompson, 2000] William Mann, and Sandra Thompson. Toward a Theory of Reading Between the lines. 7th IPRA Conference. 2000.
[Mann and Thompson, 2002] William Mann, and Sandra Thompson. Two Views of Rhetorical Structure Theory. www-rcf.usc.edu/~billmann/Wmlinguistic. 2002.
[Mann et al., 1992] William Mann, Christian Matthiessen,and Sandra Thompson. Rhetorical Structure Theory and Text Analysis. In W. C. Mann & S. A. Thompson (Eds.).Discourse Description: Diverse Linguistic Analyses of a Fund-Raising Text (pp. 39-78). Amsterdam and Philadelphia: John Benjamins. 1992.
[Mann, 2005] William Mann. 2005. RST Web Site, now http://www.sfu.ca/rst
[Marcu et al., 1999] Marcu, Daniel, Estibaliz Amorrotu and Magdalena Romera. 1999. Experiments in Constructing a Corpus of Discourse Trees. ACL'99 Workshop on Standards and Tools for Discourse Tagging. Maryland: 48-57.http://www.isi.edu/~marcu/papers.html
[Marcu and Echihabi, 2002] Daniel Marcu, A. Echihabi. An unsupervised Approach to recognizing discourse relations. In Proceedings of ACL Philadelphia. 2002.
[Marcu et al., 2002] Daniel Marcu, Magdalena Romera and Estibaliz Amorrortu. Experiments in constructing a corpus of discourse trees: problems, annotation choices, issues. www.isi.edu/~marcu.2002.
[Marcu, 1996] Daniel Marcu. Towards a synthesis of two accounts of discourse structure. Computational Linguistics. 22(3): 409-419. 1996.
[Marcu, 1997] Daniel Marcu. The Rhetorical Parsing,Summarization and Generation of Natural Texts, Phd dissertation, University of Toronto. 1997.
[Marcu, 1999a] Daniel Marcu. Discourse trees are good indicators of importance in text. In: I. Mani and M. Maybury (eds.): Advances in Automatic Text Summarization, 123-136, The MIT Press. 1999.
[Marcu, 1999b] Daniel Marcu. Instructions for manually annotating the discourse structures of texts. www.isi.edu/~marcu.1999.
[Marcu, 2000a] Daniel Marcu. The Theory and Practice of Discourse Parsing and Summarization. The MIT Press. 2000.
[Marcu, 2000b] Daniel Marcu. The Rhetorical Parsing of Unrestricted Texts: a surface-based approach. Computational Linguistics 26(3): 395-448. 2000.
[Marcu, 2002] Daniel Marcu. An Empirical Study in Multilingual Natural Language Generation:What Should A Text Planner Do?2002.
[Matthiessen and Thompson, 1988], Christian M. I. Matthiessen and Sandra Thompson. The structure of discourse and "subordination". In J. Haiman & S. A. Thompson (Eds.), Clause Combining in Discourse and Grammar. pp. 275-329. Amsterdam and Philadelphia: John Benjamins. 1988.
[Matthiessen, 1995] C.M.I.M. Matthiessen. Lexicogrammatical Cartography: English Systems, Tokyo, International Language Sciences. 1995.
[Mckeown, 1985] Kathleen R. McKeown. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge: Cambridge University Press. 1985.
[Miltsakaki et al., 2004] Eleni Miltsakaki, Rashmi Prasad, Aravind Joshi, Bonnie Webber. The Penn Discourse Treebank. ACL 2004.
[Mitkov et al., 2000] Ruslan Mitkov, E. Evans, C. Orasan, C. Barbu, L. Jones, and V. Sotirova. Conference and Anaphora: developing annotating tools, annotated resources and annotation strategies. In Proceedings of the Discourse Anaphora and Anaphora Resolution Colloquium. Lancaster.2000.
[Moore and Paris, 1983] Moore, Johanna D. and Cecile L. Paris. Planning text for advisory dialogues: Capturing intentional and rhetorical information. Computational Linguistics, 19(4):651-695. 1993.
[Moore and Pollack, 1992] Johanna Moore and M.Pollack. A Problem for RST: The need for multi-level discourse analysis. Computational Linguistics. 18(4) :537 ~544. 1992.
[Moser and Moore, 1995] Megan Moser and Johanna Moore. Instructions for coding explanations: Identifying Instructions, relations and minimal units, Technical Report 96-17, University of Pittsburgh. 1995.
[Moser and Moore, 1996] Megan Moser and Johanna Moore. Towards a synthesis of two accounts of discourse structure. Computational Linguistics, 22(3): 409-419. 1996.
[Munteanu and Marcu, 2005] Dragos Munteanu and Daniel Marcu. Improving Machine Translation Performance by Exploiting Comparable Corpora. Computational Linguistics, 31 (4), pp. 477-504, December 2005.
[Nicholas, 1994] Nick Nicholas. Problems in the application of Rhetorical Structure Theory to text generation. Master’s thesis, University of Melbourne, June 1994.
[Nicholas, 1995] Nick Nicholas. Parameters for Rhetorical Structure Theory Ontology. www.arts.unimelb.edu.au/Dept/LALX/publications/rst_ontology.html.1995.
[Nunberg, 1990] Geoffrey Nunberg. The Linguistics of Punctuation. Standford, California: CSLI Publications. 1990.
[O’Donnell et al.,2001] Micheal O'Donnell, C.Mellish, J.Oberlander, and A. Knott. ILEX: An architecture for a dynamic Hypertext generation system. Natural Language Engineering. 7, pp.225-250. 2001.
[O’Donnell,1997] Michael O’Donnell. RST–Tool: An RST analysis tool. In Proceedings of the 6th European Workshop on Natural Language Generation, Gerhard-Mercator University, Duisburg, Germany. 1997.
[Ono et al., 1994] Kenji Ono, Kazuo Sumita and Sejii Miike. Abstract Generation based on Rhetorical Structure Extraction. In Proceedings of International Conference on Computational Linguistics, Japan. pp. 344-348. 1994.
[Pardo et al., 2004] Pardo, Thiago Alexandre Salgueiro, Maria das Gracas Volpe Nunes and Lucia Helena Machado Rino. DiZer: An automatic discourse analyzer for Brazilian Portuguese. In Proceedings of First International Workshop on Natural Language Understanding and Cognitive Science (NLUCS 2004). Porto, Portugal. 2004.
[Polanyi, 1988] L.Polanyi. A formal model of the structure of discourse. Journal of Pragmatics. 12, 601-638. 1988.
[Ramsay, 2001] Guy Ramsay. Rhetorical Styles and Newstexts: A Contrastive Analysis of Rhetorical Relations in Chinese and Australian News-journal Text. http://www.arts.unsw.edu.au/languages/asaa_ejournal. 2001.
[Redeker, 1990] Gisela Redeker. Ideational and Pragmatic Markers of Discourse Structure. Journal of Pragmatics. 14: 367-381. 1990.
[Redeker, 1991] Gisela Redeker. Review article: Linguistic markers of linguistic structure. Linguistics, 29(6), 1139-1172.1991.
[Reitter and Stede, 2003] David Reitter and Manfred Stede. Step by step: Underspecified markup in incremental rhetorical analysis, Proceedings of EACL 4th International Workshop on Interpreted Corpora. Budapest, Hungary. 2003.
[Reitter, 2003a] David Reitter. Rhetorical Analysis with Rich-Feature Support Vector Models. University of Potsdam, Diploma thesis in computational linguistics. 2003.
[Reitter, 2003b] David Reitter. Simple signals for complex rhetorics: On rhetorical analysis with rich feature support vector models. Journal for Computational Linguistics and Language Technology. 18(1-2), 38-52. 2003.
[Sanders et al., 1992] Sanders, T., W. Spooren and L. Noordman. Toward a Taxonomy of Coherence Relations. Discourse Processes 15: 1-35. 1992.
[Sanders et al., 1993] Sanders, T., W. Spooren and L. Noordman. Coherence Relations in a Cognitive Theory of Discourse Representation. Cognitive Linguistics 4: 93-104. 1993.
[Sanders et al., 2001] Ted Sanders, J. Schilperoord & W. Spooren (Eds). Text Representation: Linguistic and Psycholinguistic Aspects. Amsterdam and Philadelphia: John Benjamins. 2001.
[Sanders, 1997] Ted Sanders. Semantic and Pragmatic Sources of Coherence: On the Categorization of Coherence Relations in Text. Discourse Processes 24: 119-147. 1997.
[Say and Akman, 1997] B. Say and V. Akman. Current apporaches to punctuation in computational linguistics. Computers and the Humanities, 30(6), 457-469. 1997.
[Say, 1998] Bilge Say. An Information-Based Approach to Puncutuation. Unpublished Ph. D. dissertation, Bilkent University, Ankara, Turkey. http://www.cs.bilkent.edu.tr/~say/bilge.html. 1998.
[Schauer and Hahn, 2001] Schauer, Holger and Udo Hahn.. Anaphoric cues for coherence relations, Proceedings of International Euroconference 'Recent Advances in Natural Language Processing',RANLP 2001. pp. 228-234.. Tzigov Chark, Bulgaria. 2001.
[Schiffrin, 1987] Deborah Schiffrin. Discourse Markers. Cambridge: Cambridge University Press. 1987.
[Scollon and Scollon, 1997] Ron Scollon and Suzanne Wong Scollon. Point of view and citation: Fourteen Chinese and English versions of the ‘same’ news story. Text, 17 (1), 83-125. 1997.
[Soricut and Marcu, 2003] Soricut, R., & Marcu, D. Sentence level discourse parsing using syntactic and lexical information, Proceedings of Human Language Technology and North American Association for Computational Linguistics Conference (HLTNAACL' 2003).Edmonton, Canada.
[Sperber and Wilson, 1995] Dan Sperber,and Deirdre Wilson. Relevance: Communication and Cognition.(2nd edition). Oxford: Blackwell. 1995.
[Stede and Heintze, 2004] Manfred Stede and Silvan Heintze. Machine-assisted rhetorical structure annotation. 2004.
[Stede, 2004] Manfred Stede. The Potsdam Commentary Corpus. In Proceedings of the ACL 2004 Workshop ‘Discourse Annotation’, Barcelona. 2004.
[Steed, 2003] Manfred Stede. Surfaces and depths in text understanding : the case of newspaper commentary. In Proceedings of the HLT/NAACL Workshop on Text Mining, Edmonton/AL. 2003.
[Stent, 2000] Amanda Stent. 2000. Rhetorical structure in dialog. In proceedings of 2nd International Natural Language Generation Conference 2000.
[Sumita et al., 1992] K.Sumita, K.Ono, T. Chino and S. Amano. A discourse structure analyzer for Japanese text. Proceedings of the International Conference on Fifth Generation Computer Systems. 1133-1140. 1992.
[T’sou et al., 2000] Benjamin K. T’sou, Tom B.Y. Lai, Samuel W.K. Chan, Weijun Gao, and Xuegang Zhan. Enhancement of Chinese discourse marker tagger with C4.5. In Proceedings of the Second Chinese Language Processing Workshop’ Hong Kong. 38-45. 2000.
[Taboada and Mann, 2006a] Maite Taboada and William Mann. Applications of Rhetorical Structure Theory. Discourse Studies. 2006 (to appear) .
[Taboada and Mann, 2006b] Maite Taboada and William Mann. Rhetorical Structure Theory : Looking Back and Moving Ahead. Discourse Studies. 2006 (To appear) .
[Taboada, 2004] Maite Taboada. Rhetorical relations in dialogue: A contrastive study. In C. L. Moder & A. Martinovic -Zic (Eds.), Discourse across Languages and Cultures. Amsterdam and Philadelphia: John Benjamins. 2004.
[Taboada, 2006] Maite Taboada. Discourse Markers as Signals (or Not) of Rhetorical Relations. Journal of Pragmatics, 2006 (to appear).
[Taylor, 2002] P. J. Taylor. A partial order scalogrm analysis of communication behavior in crisis negotiation with the prediction of outcome. International Journal of Conflict Management. 13(1). 4-37. 2002.
[Thomas and Short, 2000?] Jenny Thomas and Mick Short. Using Corpora for Language Research. Foreign Languages Teaching and Research Press.
[Tsou et al., 1996] Benjamin K. T’sou, Lin H. L., Ho H. C., Lai T. and Chan T. Automated Chinese Full-text Abstraction Based on Rhetorical Structure Analysis. Computer Processing of Oriental Languages. 10(2):225-238. 1996.
[Wang, 2002] Yu-Fang Wang:The preferred information sequences of adverbial linking in Mandarin Chinese discourse. Text. 22(1):141–172. 2002.
[Webber et al., 1999] Bonnie Webber, Alistair Knott, Matthew Stone and Aravind Joshi. Discourse Relations: A Structural and Presuppositional Account Using Lexicalized TAG. 37th Annual Meeting of the Association for Computational Linguistics. College Park, Maryland, USA, Association for Computational Linguistics: 41-48. 1999.
[Webster, 1994] Jonathan Webster. A Functional Semantic Processor for Chinese and English Texts. Proceedings of the 1994 International Conference on Computer Processing of Oriental Languages. Pp.269-273. 1994.
[Webster, 2002] Jonathan Webster. Text Linguistics (《篇章语言学》,徐赳赳译).中国社会科学出版社. 2002.
[Williams and Reiter, 2003] Sandra Williams and Ehud Reiter. A corpus analysis of discourse relations for natural language generation. In Proceedings of Corpus Linguistics, 2003.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. A response to Marcu (2003). Discourse structure: trees or graphs? Unpublished manuscript, MIT, Cambridge, MA. 2004.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. Paragraph-, word-, and coherence-based approaches to sentence ranking: A comparison of algorithm and human performance, Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics. Barcelona, Spain. 2004.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. Representing discourse coherence: A corpus-based analysis, Proceedings of the 20th International Conference on Computational Linguistics (COLING). Geneva, Switzerland. 2004.
[Yue and Feng, 2005] Findings in a Preliminary Study on the Rhetorical Structure of Chinese TV News, Proceedings of 1st Conference of Systemic Functional Grammar (CFSG05), Pp. 29-38. Sydney Australia. July 2005.
[Yue, 2006] Discursive Usage of Six Chinese Punctuation Marks. In Proceedings of COLING/ACL-2006 Student Research Workshop. Sydney Australia. July 2006.
[Zhu,2003] Zhu Yunxia (2003). Incorporating Persuasive Orientations into the Cross-Cultural Study of Genres. Web Proceedings of“Knowledge & Discourse: Speculating on Disciplinary Futures”, 2nd International Conference, Hong Kong. June 2002.
[曹,1995] 曹逢甫。《主题在汉语中的功能研究》(谢天蔚译)。1995。语文出版社。
[陈,2004] 陈群秀。信息处理用现代汉语虚词义类词典研究和工作单设计。《新加坡会议论文集》。 2004 年 7 月。
[陈、邱,1997] 陈忠华、邱国旺。修辞结构理论与修辞结构分析评介。《外语研究》。1997 年 03 期
[戴、薛,2004] 戴炜华、薛雁。修辞体裁分析和修辞结构论。《外语教学》。2004 年第3 期。
[邓,2004] 邓瑜。新闻评论界说新探。我写传媒网 2004-5-28 发布。
[丁,1997] 丁法章(主编)。《新闻评论学》。复旦大学出版社。1997。
[范,1998] 范荣康。《新闻评论学》。人民日报出版社。1988。
[方,2002] 方梅。指示词这和那在北京话中的语法化。《中国语文》2002 年第 4 期。
[冯,2004] 冯光武。汉语语用标记的语义、语用分析,《现代外语》2004 年第 1 期。
[冯,1996] 冯志伟。《自然语言的计算机处理》。上海:上海外语教育出版社。1996。
[冯,1999] 冯志伟。《现代语言学流派》。陕西人民出版社。1999。
[高,1986b] 高名凯。《汉语语法论》。商务印书馆。1986。
[高等,2000] 高维君、姚天顺、黎邦洋、陈伟光、邹嘉彦。机器学习在汉语关联词语识别中的应用。《中文信息学报》。第 14 卷第 3 期,第 1-8 页。2000。
[龚,2000] 龚千炎。《中国语法学史》。语文出版社。2000。
[郭,1999] 郭志良。《现代汉语转折词语研究》。北京语言文化大学出版社。1999。
[郭等,1994] 郭志林等。《应用写作手册》。吉林大学出版社。1994。
[郭等,2003] 郭忠伟、徐延勇、周献中。基于 Schema 和 RST 的自然语言生成混合规划方法。《计算机工程》。2003 年 06 期。
[郝,1983] 郝长留。《语段知识》。语文出版社。1983。
[胡,1996] 胡裕树(主编)。《现代汉语(重订本)》。上海:上海教育出版社。1996。
[胡等,1998] 胡文龙、秦珪、涂光晋。《新闻评论教程》。中国人民大学出版社。1998。
[胡,1994] 胡壮麟(编著)。《语篇的衔接与连贯》。上海:上海外语教育。1994。
[胡,2000] 胡壮麟。《功能主义纵横谈》。北京:外语教学与研究出版社。2000。
[黄,1988] 黄国文(编著)。《语篇分析概要》。湖南教育出版社。1988。
[黄,2001] 黄大网。话语标记研究综述。《福建外语》。2001 年第 1 期。
[黄、李,2002] 黄昌宁、李涓子。《语料库语言学》。商务印书馆。2002。
[黄、廖,2001] 黄伯荣、廖序东(主编)。《现代汉语》(增订二版)。高等教育出版社。2001。
[兰,2002] 兰宾汉。《汉语语法分析的理论与实践》。中国社会科学出版社。2002。 汉语财经评论的修辞结构标注及篇章分析
[黎,1924/2000] 黎锦熙。《新著国语文法》。商务印书馆。1924/2000。
[黎、刘,1962] 黎锦熙、刘世儒。《汉语语法教材》商务印书馆。1962。
[李,1997] 李宇明。汉语语法“本位”论评——兼评邢福义“小句中枢说”。《世界汉语教学》。1:16~23。1997。
[梁,2002] 梁敬美。“这_”和“那_”研究。中国社会科学院博士论文。2002。
[廖,1992] 廖秋忠。《廖秋忠文集》。北京语言学院出版社。1992。
[林,1987] 林裕文。《偏正复句》。《汉语知识讲话》(合订本 5)。上海教育出版社。1987。
[林,2000] 林穗芳。《标点符号学习与应用》。人民出版社。2000。
[刘,1997] 刘挺、吴岩、王开铸。基于信息抽取和文本生成的自动文摘系统设计。《情报学报》。1997 年 1 期。
[刘,2003] 刘世铸、张征。修辞结构理论与 RST 工具。《外语电化教学》。2003 年 4 期
[刘,2005]人民日报经济新闻版主编刘磊访谈实录。 www.people.com.cn。
[陆、马,1985] 陆俭明、马真。《现代汉语虚词散论》。北京大学。1985。
[陆、沈,2003] 陆俭明、沈阳。《汉语和汉语研究十五讲》。北京大学出版社。2003。
[吕,1942/1882] 吕叔湘。《中国文法要略》。商务印书馆。1982。
[吕,1979] 吕叔湘。《汉语语法论文集(增订本)》。商务印书馆。1984。
[吕,1999] 吕叔湘(主编)。《现代汉语八百词(增订本)》。商务印书馆。1999。
[吕,1983] 吕冀平。《汉语语法基础》。黑龙江人民出版社。1983。
[马,1898/2002] 马建忠。《马氏文通》。商务印书馆。1898/2002。
[马,2003] 马广惠。国外对比修辞研究 36 年述评。《山东外语教学》。2003 年 03 期
[梅,1996] 梅汉成。现代汉语句群研究概述。《盐城师专学报(哲社版)》。1996 年第03 期。
[聂,2003] 聂仁发。《现代汉语语篇研究》。湖南师范大学博士论文。2003 年 9 月。
[邵,2001] 邵敬敏。《现代汉语通论》。上海教育出版社。2001。
[沈,1987] 沈开木。《句段分析》。语文出版社。1987。
[苏,1999] 苏培成。《标点符号实用手册》。语文出版社。1999。
[涂,1998] 涂光晋。《广播电视评论学》。新华出版社。1998。
[王,1943] 王力。《中国现代语法》(1943)。《王力文集》(第二卷)重印。山东教育出版社。1985。
[王,1994] 王福祥。《话语语言学概论》。外语教学与研究出版社。1994。
[王,1994] 王伟。“修辞结构理论”评介(上)。《国外语言学》。1994 年第 4 期。
[王,1995] 王伟。“修辞结构理论”评介(下)。《国外语言学》。 1995 年第 2 期。
[王,1997] 王振业。《广播电视新闻评论》。北京广播学院出版社。1997。
[王,2001] 王一禾。2001。 符号小,学问大——写在《标点符号学习与应用》重印之际。 http://www。epsalon。com/printpage。asp?ArticleID=957
[王,2001] 王水莲。修辞结构理论与 AND 结构的语篇功能,《外语与外语教学》。2001年 03 期
[王、白,1989] 王福祥、白春仁 (主编)。《话语语言学论文集》。外语教学与研究出版社。1989。
[王、董,1995] 王伟、董冀平。修辞结构理论与系统功能语言学──两种功能语言理论比较。《山东外语教学》。1995 年 02 期。
[王、胡,2000] 王振业、胡平。2000。《新闻评论写作教程》。中国广播电视出版社。
[王等,1994] 王维贤、张学成、卢曼云、程怀友。《现代汉语复句新解》。 1994。华东师范大学出版社。
[吴,1993] 吴为章。《实用语法修辞》。北京广播学院出版社。1993。
[吴,1997] 吴为章。《广播电视话语研究选集》。北京广播学院出版社。1997。
[吴,2001] 吴启主。《汉语构件语篇学》。岳麓书社。2001。
[吴、田,2000] 吴为章,田小琳。《汉语句群》。商务印书馆。2000。
[夏,2003] 夏蓉。从修辞结构理论看前指在篇章中的分布。《外语与外语教学》。2003年 10 期。
[肖,2003] 肖莉。近百年中国新闻评论得失谈。复旦大学硕士论文。2003。
[邢,2000] 邢福义。《汉语语法学》,东北师范大学出版社。2000。
[邢,2002] 邢福义。《汉语复句研究》。商务印书馆。2002。
[徐,1995] 徐赳赳。话语分析二十年。《外语教学与研究》。1995 年第 1 期。
[徐,1997] 徐赳赳。话语分析在中国。《外语教学与研究》。1997 年第 4 期:20-24。
[徐,2003] 徐赳赳。《现代汉语篇章回指研究》。中国社会科学出版社。2003。
[徐、Webster,1999] 徐赳赳、J. Webster。复句研究与修辞结构理论。《外语教学与研究》,1999。4 :16-22。
[许,2005] 许家金。《青少年汉语口语中话语标记的话语功能研究》。北京外国语大学博士学位论文。2005 年 10 月。
[许,2004] 许余龙。《篇章回指的功能语用探索》。上海:上海外语教育出版社。2004。
[杨,2004] 杨坚定、钟莉莉。动态翻译单位探讨。《中国翻译》。2004 年 05 期。
[姚等,2002] 姚天顺、朱靖波、张俐、杨莹。《自然语言理解—一种让机器懂得人类语言的研究(第二版)》。清华大学出版社,2002。
[尹,2004] 尹汉生。论新闻评论发展趋势。《求索》2004。10
[袁等,1994] 袁晖(主编)。《标点符号词典》。山西人民出版社。1994。
[张,1959] 张志公。《汉语知识》人民教育出版社。1959。
[张,1985] 张寿康。《文章学导论》,湖北教育出版社。1985。
[张, 2000] 张益民。基于混合方法的中文文本解释研究。上海交通大学博士论文。1998。
[张,2000a] 张益民、陆汝占、沈李斌。一种混合型的汉语篇章结构自动分析方法。《软件学报》。2000 年 11 期。
[张,2004] 张德禄。系统功能语言学的新发展。《当代语言学》2004 年第一期:57—65。
[周,2002] 周刚。《连词与相关问题》。安徽教育出版社。2002。
[周,2003a] 周强。中文树库标注规范。《中文信息学报》。 18 (4):1-8。2004。
[周,2003b] 周静。《现代汉语递进范畴研究》。华东师范大学博士论文。
[朱,2004] 朱昆仑。修辞结构理论在大学英语阅读教学中的应用。《山东外语教学》。2004 年 02 期。
[朱,1993] 朱永生(主编)。《语言?语篇?语境:第二届全国系统功能语法研讨会论文集》。北京:清华大学出版社。1993。
[朱等,2002] 朱永生、郑立信、苗兴伟。《英汉语篇衔接手段对比研究》。上海外语教育出版社。2002。
[佐藤,1996] 佐藤一郎。《中国文章论》(赵善嘉译)。上海古籍出版社。1996。
7 该网站原来的网址为www.sil.org/~mannb/rst。在Bill Mann于2004年8月13日过世之后,由Maite Taboada负责维护,并迁址到http://www.sfu.ca/rst。
29 Songren Cui. 1986. A Comparison of English and Chinese Expository Rhetorical Structures. UCLA Master thesis.
30 R. R. Kaplan. 1966. Cultural Thought Patterns in Intercultural Communication. Language Learning. 16:1-20.
36 张志公,1962,《谈词章之学》,转引自王福祥(1989:8)。
37 张寿康,1983,‘试论文章学研究’,《汉语论丛》,转引自王福祥(1989:9)。
40 吕叔湘.《汉语语法分析问题》. 1979.商务印书馆.收录在《汉语语法论文集(增订本)》.商务印书馆. 1984. pp481-571.
41 廖秋忠(1992:120-30)“篇章中的论证结构”,原载于《语言教学与研究》1998 年第 1 期。
43 廖秋忠,“篇章与语用和句法研究”,原载于《语言教学与研究》1991 年第四期。《廖秋忠文集》(1992)转载,具体语句见第 203 页注⒁。
50 引用王一禾(2001):“符号小,学问大——写在《标点符号学习与应用》重印之际”。转载于http://www.epsalon.com/printpage.asp?ArticleID=957
[Allen,1994] James Allen. Natural Language Understanding.The Benjamin/Cummings Publishing Company. 1994.
[Bateman and Delin, 2005] John Bateman and Judy Delin. Rhetorical structure theory. In Encyclopedia of Language and Linguistics (2nd ed.). Oxford: Elsevier. 2005.
[Bateman and Rondhuis, 1997] John Bateman and K. J. Rondhuis. "Coherence relations": Toward a General Specification. Discourse Processes. 24(1): 5-50. 1997.
[Bateman et al., 2001]John Bateman, Thomas Kamps, J?rg Kleinz and Klaus Reichenberger. Towards constructive text, diagram, and layout generation for information presentation. Computational Linguistics, 2001. 27 (3), 409-449.
[Berger et al., 2002] Daniela Berger, David Reitter and Manfred Stede. XML/XSL in the Dictionary: The Case of Discourse Markers. In Proceedings of the COLING Workshop NLPXML-2002. Taipei.
[Bloomfield,1933(2002)] Leonard Bloomfield. 1933. Language. Reprinted by Foreign Language Teaching and Research Press. Beijing. 2002.
[Burstein and Marcu, 2003] J. Burstein, and Daniel Marcu. A machine learning approach for identification of thesis and conclusion statements in student essays. Computers and the Humanities. 37(4), 455-467. 2003.
[Carlson and Marcu, 2002] Lynn Carlson and Daniel Marcu. Discourse Tagging Manual. http://www.isi.edu/~marcu/discourse/tagging-ref-manual.pdf. 2002.
[Carlson et al., 2001] Carlson, Lynn, John Conroy, Daniel Marcu, Dianne O'Leary, Mary Ellen Okurowski, Anthony Taylor and William Wong. An empirical study of the relation between abstracts, extracts, and the discourse structure of texts, Proceedings of Document Understanding Conference (DUC-2001). New Orleans, Louisiana. 2001.
[Carlson et al., 2003] Lynn Carlson, Daniel Marcu, and Mary E. Okurowski. Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. In Jan van Kuppevelt and Ronnie Smith, editors, Current Directions in Discourse and Dialogue. Kluwer Academic Publishers. 2003.
[Chalker, 2000] Sylvia Chalker. Linking Words (《连词》,刘万存译). HK: Commercial Press. 2000.
[Chan et al., 2000] Samuel W. K. Chan, Tom B. Y. Lai, W. J. Gao and Benjamin K. T’sou. Mining discourse markers for Chinese Textual Summarization. Workshop on Automatic Summarization, ACL 2000.
[Chu, 1998] Chauncey C. Chu(屈承熹). A Discourse Grammar of Mandarin Chinese. Peter Lang Publishing. N.Y. 1998.
[Connor, 2002] Ulla Connor. New directions in contrastive rhetoric. Tesol Quarterly, 36 (4), 493-510. 2002.
[Corston-Oliver, 1998] Simon H. Corston-Oliver. Computing Representation of the Structure of Written Discourse. Technical Report, MSR-TR-98-15. 1998.
[Cristea and Webber, 1997] Dan Cristea and Bonnie Webber. Expectations in incremental discourse processing. Proceedings of 35th Annual Meeting of the Association for Computational Linguistics (ACL'97). Vol.1, pp.88-95. Madrid, Spain. 1997.
[Cristea et al., 2000] Cristea, Dan, Nancy Ide and Laurent Romary. Veins Theory: A model of global discourse cohesion and coherence, Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (ACL-98/COLING-98). pp. 281-285. Montréal, Canada. 1998.
[Cristea et al., 2000] Dan Cristea , Nancy Ide, Daniel Marcu and Valentin Tablan. Discourse structure and coreference: An empirical study. In Proceedings of the 18th International Conference on Computational Linguistics (COLING'00) (Vol. 1, pp. 208-214). Saarbrüken, Germany. 2000.
[Cui,1986] Songren Cui. A Comparison of English and Chinese Expository Rhetorical Structures. MA diploma thesis, UCLA. 1986.
[Dale, 1991] Robert Dale. The role of punctuation in discourse structure. Proceedings of AAAI Fall Symposium on Discourse Structure in Natural Language Understanding and Generation (pp. 13-14). Asilomar, CA. 1991.
[den Ouden, 2004] Hanny den Ouden. Prosodic Realizations of Text Structure. Ph.D. dissertation, University of Tilburg, Tilburg, The Netherlands. 2004.
[van Dijk, 1979] Teun A.van Dijk. Pragmatic connectives. Journal of Pragmatics, Vol.(3): 447-456. 1979.
[van Dijk, 1980] Teun A. van Dijk. Macrostructures: An Interdisciplinary Study of Global Structures. in Discourse Interaction and Cognition. 1980. Hillsdale, NJ: Lawrence Erlbaum.
[Fawcett an Davies, 1992] Robin P. Fawcett and Bethan L. Davies. Monologue as a turn in dialogue: Towards an integration of Exchange Structure and Rhetorical Structure Theory. In R. Dale, E. Hovy,D. R?sner and O. Stock (Eds.), Aspects of Automated Language Generation (pp. 151-166). Berlin: Springer. 1992.
[Fox, 1987] Barbara A. Fox. 1987. Discourse Structure and Anaphora: Written and Conversational English. Cambridge: Cambridge University Press.
[Fraser, 1999] Bruce Fraser. 1999. What are discourse markers? Journal of Pragmatics 31: 931-952.
[Gaddy et al., 2001] The influence of text cues on the allocation during reading. In Sanders et al. (2003).pp89-110.
[Gaizauskas et al., 2003] Rob Gaizauskas, Patrick Hans,James Pustejovsky, Roser Sauri, Andrew See, Andrea Setzer, Liser Ferro, and Beth Sundheim. The Timebank corpus. In Corpus Linguistics 2003. Lancaster. 2003.
[Germann et al., 2003]Ulrich Germann, Mike Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada. Fast Decoding and Optimal Decoding for Machine Translation. Artificial intelligence, 2003. 154 (1-2), pp. 127-143.
[Gil and Ratnakar, 2002] Gil, Y. and V. Ratnakar. TRELLIS: An interactive tool for capturing information analysis and decision making. In Knowledge Engineering and Knowledge Management,Proceedings. 2002. pp. 37-42.
[Grimes, 1975] J. E. Grimes. The Thread of Discourse. The Hague: Moulton Press. 1975.
[Grosz and Sidner, 1986] Barbara J.Grosz and C. L.Sidner. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3), 175-204. 1986.
[Halliday and Hasan, 1976] M.A.K. Halliday and Ruqaiya Hasan. 1976. Cohesion in English. London: Longman. Reprinted by Foreign Languages and Teaching Press. Beijing. 2000.
[Halliday, 1981] M.A.K. Halliday. Text Semantics and Clause Grammar: How is a Text Like a Clause ?. in Sture Allen (ed.) :Text Processing : Text Analysis and Generation, Text Typology and Attention (Proceedings of Nobel Symposium 51). Stockholm : Almqvist and Wiksell. 209-47. 1982.
[Halliday, 1985/1994] M.A.K. Halliday. An Introduction to Functional Grammar. Edward Arnold, London. 1985/1994.
[Hosti, 1969] O. R. Holsti. Content analysis for the social sciences and humanities. Reading, MA: Addison-Wesley Publishing Co. 1969.
[Hovy and Maier, 1992] Eduard Hovy and E. Maier. Parsimonious of Profligate: How Many and Which Discourse Structure Relations?. Technical Report ISI/RR-93-373. Information Sciences Institute, CA. 1992.
[Hovy, 1988] Eduard Hovy. Planning coherent multisentential text. Proceedings of 26th Annual Meeting of the Association for Computational Linguistics (ACL'88). pp. 163-169. Buffalo, New York. 1988.
[Hovy, 1990] Eduard Hovy. Parsimonious and profligate approaches to the question of discourse structure relations. 5th International Workshop on Text Generation (pp. 59-65). Pittsburgh, PA. 1990.
[Hovy, 1991] Eduard Hovy. Recent trends in computational research on monologic discourse structure. Computational Intelligence. 1991. Vol.7, pp.363-366.
[Hovy, 1993] Eduard Hovy. From interclausal relations to discourse structure- A long way behind, a long way ahead. In H. Horacek & M. Zock (Eds.), 1993. New Concepts in Natural Language Generation (pp. 57-68). London: Pinter.
[Itule and Anderson, 2003] Bruce Itule and Douglas A. Anderson. News Writing and Reporting for Today’s Media. (6th Ed.). McGraw-Hill/中国人民大学出版社. 2003.
[Jones, 1996] Bernard Jones. What’s The Point? A (Computational) Theory of Punctuation. Phd thesis. 1996.
[Kight and Marcu, 2005] Kevin Knight and Daniel Marcu. Machine Translation in Year 2004. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005. Philadelphia, PA.
[Knott and Dale, 1994] Alistair Knott and Robert Dale. Using Linguistic Phenomena to Motivate a Set of Coherence Relations. Discourse Processes. 1994. 18: 35-62.
[Knott and Sanders, 1998] Alistair Knott and T. Sanders. The classification of coherence relations and their linguistic markers: An exploration of two languages. Journal of Pragmatics. 1998. 30(2): 135-175.
[Knott et al., 2001] Alistair Knott, Jon Oberlander, Michael O'Donnell and Chris Mellish. Beyond elaboration: The interaction of relations and focus in coherent text. In T. Sanders, J. Schilperoord and W. Spooren (Eds.), Text Representation: Linguistic and Psycholinguistic Aspects. 2001. pp. 181-196. Amsterdam and Philadelphia: John Benjamins.
[Knott, 1996] Alistair Knott. A Data-Driven Methodology for Motivating a Set of Coherence Relations. Unpublished Ph.D. dissertation, University of Edinburgh, Edinburgh, UK. 1996.
[Knott, 1998] Alistair Knott. Similarity and contrast relations and inductive rules, Proceedings of ACL Workshop on Discourse Relations and Discourse Markers (pp. 54-57). Montréal, Canada. 1998.
[Kong, 1998] K.C.C. Kong. Are simple business request letters really simple? A comparison of Chinese and English business request letters. Text. Vol.18(1): 103-41. 1998.
[Le and Abeysinghe, 2003] H. T. Le and G.Abeysinghe. A Study to Improve the Efficiency of a Discourse Parsing System. CICLing 2003.
[Lindley et al., 2001] Craig Lindley, Jim Davis, Frank Nack, and Lloyd Rutledge. The application of rhetorical structure theory to interactive news program generation from digital archives. Technical Report INS-R0101, CWI Centrum voor Wiskunde en Informatica, January 2001.
[Longacre, 1983] R. E.Longacre. The Grammar of Discourse. New York: Plenum. 1983.
[Maier and Hovy, 1991] Elisabeth Maier and Eduard Hovy. A metafunctionally motivated taxonomy for discourse structure relations, Proceedings of 3rd European Workshop on Language Generation. 1991.Innsbruck, Austria.
[Mann and Thompson, 1983] William Mann, and Sandra Thompson. Relational Propositions in Discourse. Information Sciences Institute of University of Southern California, Los Angeles, ISI/RR-83-115, 1-28. 1983.
[Mann and Thompson, 1987a] William Mann, and Sandra Thompson. Rhetorical Structure Theory: A Theory of Text Organization: ISI/RS-87-190. Information Sciences Institute, University of Southern California. 1987.
[Mann and Thompson, 1987b] William Mann, and Sandra Thompson. Rhetorical Structure Theory: A Framework for the Analysis of Texts." IPRA Papers in Pragmatics 1: 1-21. 1987."
[Mann and Thompson, 1988] William Mann, and Sandra Thompson. Rhetorical Structure Theory: Toward a functional theory of text organization. Text. 8(3):243-281. 1988.
[Mann and Thompson, 2000] William Mann, and Sandra Thompson. Toward a Theory of Reading Between the lines. 7th IPRA Conference. 2000.
[Mann and Thompson, 2002] William Mann, and Sandra Thompson. Two Views of Rhetorical Structure Theory. www-rcf.usc.edu/~billmann/Wmlinguistic. 2002.
[Mann et al., 1992] William Mann, Christian Matthiessen,and Sandra Thompson. Rhetorical Structure Theory and Text Analysis. In W. C. Mann & S. A. Thompson (Eds.).Discourse Description: Diverse Linguistic Analyses of a Fund-Raising Text (pp. 39-78). Amsterdam and Philadelphia: John Benjamins. 1992.
[Mann, 2005] William Mann. 2005. RST Web Site, now http://www.sfu.ca/rst
[Marcu et al., 1999] Marcu, Daniel, Estibaliz Amorrotu and Magdalena Romera. 1999. Experiments in Constructing a Corpus of Discourse Trees. ACL'99 Workshop on Standards and Tools for Discourse Tagging. Maryland: 48-57.http://www.isi.edu/~marcu/papers.html
[Marcu and Echihabi, 2002] Daniel Marcu, A. Echihabi. An unsupervised Approach to recognizing discourse relations. In Proceedings of ACL Philadelphia. 2002.
[Marcu et al., 2002] Daniel Marcu, Magdalena Romera and Estibaliz Amorrortu. Experiments in constructing a corpus of discourse trees: problems, annotation choices, issues. www.isi.edu/~marcu.2002.
[Marcu, 1996] Daniel Marcu. Towards a synthesis of two accounts of discourse structure. Computational Linguistics. 22(3): 409-419. 1996.
[Marcu, 1997] Daniel Marcu. The Rhetorical Parsing,Summarization and Generation of Natural Texts, Phd dissertation, University of Toronto. 1997.
[Marcu, 1999a] Daniel Marcu. Discourse trees are good indicators of importance in text. In: I. Mani and M. Maybury (eds.): Advances in Automatic Text Summarization, 123-136, The MIT Press. 1999.
[Marcu, 1999b] Daniel Marcu. Instructions for manually annotating the discourse structures of texts. www.isi.edu/~marcu.1999.
[Marcu, 2000a] Daniel Marcu. The Theory and Practice of Discourse Parsing and Summarization. The MIT Press. 2000.
[Marcu, 2000b] Daniel Marcu. The Rhetorical Parsing of Unrestricted Texts: a surface-based approach. Computational Linguistics 26(3): 395-448. 2000.
[Marcu, 2002] Daniel Marcu. An Empirical Study in Multilingual Natural Language Generation:What Should A Text Planner Do?2002.
[Matthiessen and Thompson, 1988], Christian M. I. Matthiessen and Sandra Thompson. The structure of discourse and "subordination". In J. Haiman & S. A. Thompson (Eds.), Clause Combining in Discourse and Grammar. pp. 275-329. Amsterdam and Philadelphia: John Benjamins. 1988.
[Matthiessen, 1995] C.M.I.M. Matthiessen. Lexicogrammatical Cartography: English Systems, Tokyo, International Language Sciences. 1995.
[Mckeown, 1985] Kathleen R. McKeown. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge: Cambridge University Press. 1985.
[Miltsakaki et al., 2004] Eleni Miltsakaki, Rashmi Prasad, Aravind Joshi, Bonnie Webber. The Penn Discourse Treebank. ACL 2004.
[Mitkov et al., 2000] Ruslan Mitkov, E. Evans, C. Orasan, C. Barbu, L. Jones, and V. Sotirova. Conference and Anaphora: developing annotating tools, annotated resources and annotation strategies. In Proceedings of the Discourse Anaphora and Anaphora Resolution Colloquium. Lancaster.2000.
[Moore and Paris, 1983] Moore, Johanna D. and Cecile L. Paris. Planning text for advisory dialogues: Capturing intentional and rhetorical information. Computational Linguistics, 19(4):651-695. 1993.
[Moore and Pollack, 1992] Johanna Moore and M.Pollack. A Problem for RST: The need for multi-level discourse analysis. Computational Linguistics. 18(4) :537 ~544. 1992.
[Moser and Moore, 1995] Megan Moser and Johanna Moore. Instructions for coding explanations: Identifying Instructions, relations and minimal units, Technical Report 96-17, University of Pittsburgh. 1995.
[Moser and Moore, 1996] Megan Moser and Johanna Moore. Towards a synthesis of two accounts of discourse structure. Computational Linguistics, 22(3): 409-419. 1996.
[Munteanu and Marcu, 2005] Dragos Munteanu and Daniel Marcu. Improving Machine Translation Performance by Exploiting Comparable Corpora. Computational Linguistics, 31 (4), pp. 477-504, December 2005.
[Nicholas, 1994] Nick Nicholas. Problems in the application of Rhetorical Structure Theory to text generation. Master’s thesis, University of Melbourne, June 1994.
[Nicholas, 1995] Nick Nicholas. Parameters for Rhetorical Structure Theory Ontology. www.arts.unimelb.edu.au/Dept/LALX/publications/rst_ontology.html.1995.
[Nunberg, 1990] Geoffrey Nunberg. The Linguistics of Punctuation. Standford, California: CSLI Publications. 1990.
[O’Donnell et al.,2001] Micheal O'Donnell, C.Mellish, J.Oberlander, and A. Knott. ILEX: An architecture for a dynamic Hypertext generation system. Natural Language Engineering. 7, pp.225-250. 2001.
[O’Donnell,1997] Michael O’Donnell. RST–Tool: An RST analysis tool. In Proceedings of the 6th European Workshop on Natural Language Generation, Gerhard-Mercator University, Duisburg, Germany. 1997.
[Ono et al., 1994] Kenji Ono, Kazuo Sumita and Sejii Miike. Abstract Generation based on Rhetorical Structure Extraction. In Proceedings of International Conference on Computational Linguistics, Japan. pp. 344-348. 1994.
[Pardo et al., 2004] Pardo, Thiago Alexandre Salgueiro, Maria das Gracas Volpe Nunes and Lucia Helena Machado Rino. DiZer: An automatic discourse analyzer for Brazilian Portuguese. In Proceedings of First International Workshop on Natural Language Understanding and Cognitive Science (NLUCS 2004). Porto, Portugal. 2004.
[Polanyi, 1988] L.Polanyi. A formal model of the structure of discourse. Journal of Pragmatics. 12, 601-638. 1988.
[Ramsay, 2001] Guy Ramsay. Rhetorical Styles and Newstexts: A Contrastive Analysis of Rhetorical Relations in Chinese and Australian News-journal Text. http://www.arts.unsw.edu.au/languages/asaa_ejournal. 2001.
[Redeker, 1990] Gisela Redeker. Ideational and Pragmatic Markers of Discourse Structure. Journal of Pragmatics. 14: 367-381. 1990.
[Redeker, 1991] Gisela Redeker. Review article: Linguistic markers of linguistic structure. Linguistics, 29(6), 1139-1172.1991.
[Reitter and Stede, 2003] David Reitter and Manfred Stede. Step by step: Underspecified markup in incremental rhetorical analysis, Proceedings of EACL 4th International Workshop on Interpreted Corpora. Budapest, Hungary. 2003.
[Reitter, 2003a] David Reitter. Rhetorical Analysis with Rich-Feature Support Vector Models. University of Potsdam, Diploma thesis in computational linguistics. 2003.
[Reitter, 2003b] David Reitter. Simple signals for complex rhetorics: On rhetorical analysis with rich feature support vector models. Journal for Computational Linguistics and Language Technology. 18(1-2), 38-52. 2003.
[Sanders et al., 1992] Sanders, T., W. Spooren and L. Noordman. Toward a Taxonomy of Coherence Relations. Discourse Processes 15: 1-35. 1992.
[Sanders et al., 1993] Sanders, T., W. Spooren and L. Noordman. Coherence Relations in a Cognitive Theory of Discourse Representation. Cognitive Linguistics 4: 93-104. 1993.
[Sanders et al., 2001] Ted Sanders, J. Schilperoord & W. Spooren (Eds). Text Representation: Linguistic and Psycholinguistic Aspects. Amsterdam and Philadelphia: John Benjamins. 2001.
[Sanders, 1997] Ted Sanders. Semantic and Pragmatic Sources of Coherence: On the Categorization of Coherence Relations in Text. Discourse Processes 24: 119-147. 1997.
[Say and Akman, 1997] B. Say and V. Akman. Current apporaches to punctuation in computational linguistics. Computers and the Humanities, 30(6), 457-469. 1997.
[Say, 1998] Bilge Say. An Information-Based Approach to Puncutuation. Unpublished Ph. D. dissertation, Bilkent University, Ankara, Turkey. http://www.cs.bilkent.edu.tr/~say/bilge.html. 1998.
[Schauer and Hahn, 2001] Schauer, Holger and Udo Hahn.. Anaphoric cues for coherence relations, Proceedings of International Euroconference 'Recent Advances in Natural Language Processing',RANLP 2001. pp. 228-234.. Tzigov Chark, Bulgaria. 2001.
[Schiffrin, 1987] Deborah Schiffrin. Discourse Markers. Cambridge: Cambridge University Press. 1987.
[Scollon and Scollon, 1997] Ron Scollon and Suzanne Wong Scollon. Point of view and citation: Fourteen Chinese and English versions of the ‘same’ news story. Text, 17 (1), 83-125. 1997.
[Soricut and Marcu, 2003] Soricut, R., & Marcu, D. Sentence level discourse parsing using syntactic and lexical information, Proceedings of Human Language Technology and North American Association for Computational Linguistics Conference (HLTNAACL' 2003).Edmonton, Canada.
[Sperber and Wilson, 1995] Dan Sperber,and Deirdre Wilson. Relevance: Communication and Cognition.(2nd edition). Oxford: Blackwell. 1995.
[Stede and Heintze, 2004] Manfred Stede and Silvan Heintze. Machine-assisted rhetorical structure annotation. 2004.
[Stede, 2004] Manfred Stede. The Potsdam Commentary Corpus. In Proceedings of the ACL 2004 Workshop ‘Discourse Annotation’, Barcelona. 2004.
[Steed, 2003] Manfred Stede. Surfaces and depths in text understanding : the case of newspaper commentary. In Proceedings of the HLT/NAACL Workshop on Text Mining, Edmonton/AL. 2003.
[Stent, 2000] Amanda Stent. 2000. Rhetorical structure in dialog. In proceedings of 2nd International Natural Language Generation Conference 2000.
[Sumita et al., 1992] K.Sumita, K.Ono, T. Chino and S. Amano. A discourse structure analyzer for Japanese text. Proceedings of the International Conference on Fifth Generation Computer Systems. 1133-1140. 1992.
[T’sou et al., 2000] Benjamin K. T’sou, Tom B.Y. Lai, Samuel W.K. Chan, Weijun Gao, and Xuegang Zhan. Enhancement of Chinese discourse marker tagger with C4.5. In Proceedings of the Second Chinese Language Processing Workshop’ Hong Kong. 38-45. 2000.
[Taboada and Mann, 2006a] Maite Taboada and William Mann. Applications of Rhetorical Structure Theory. Discourse Studies. 2006 (to appear) .
[Taboada and Mann, 2006b] Maite Taboada and William Mann. Rhetorical Structure Theory : Looking Back and Moving Ahead. Discourse Studies. 2006 (To appear) .
[Taboada, 2004] Maite Taboada. Rhetorical relations in dialogue: A contrastive study. In C. L. Moder & A. Martinovic -Zic (Eds.), Discourse across Languages and Cultures. Amsterdam and Philadelphia: John Benjamins. 2004.
[Taboada, 2006] Maite Taboada. Discourse Markers as Signals (or Not) of Rhetorical Relations. Journal of Pragmatics, 2006 (to appear).
[Taylor, 2002] P. J. Taylor. A partial order scalogrm analysis of communication behavior in crisis negotiation with the prediction of outcome. International Journal of Conflict Management. 13(1). 4-37. 2002.
[Thomas and Short, 2000?] Jenny Thomas and Mick Short. Using Corpora for Language Research. Foreign Languages Teaching and Research Press.
[Tsou et al., 1996] Benjamin K. T’sou, Lin H. L., Ho H. C., Lai T. and Chan T. Automated Chinese Full-text Abstraction Based on Rhetorical Structure Analysis. Computer Processing of Oriental Languages. 10(2):225-238. 1996.
[Wang, 2002] Yu-Fang Wang:The preferred information sequences of adverbial linking in Mandarin Chinese discourse. Text. 22(1):141–172. 2002.
[Webber et al., 1999] Bonnie Webber, Alistair Knott, Matthew Stone and Aravind Joshi. Discourse Relations: A Structural and Presuppositional Account Using Lexicalized TAG. 37th Annual Meeting of the Association for Computational Linguistics. College Park, Maryland, USA, Association for Computational Linguistics: 41-48. 1999.
[Webster, 1994] Jonathan Webster. A Functional Semantic Processor for Chinese and English Texts. Proceedings of the 1994 International Conference on Computer Processing of Oriental Languages. Pp.269-273. 1994.
[Webster, 2002] Jonathan Webster. Text Linguistics (《篇章语言学》,徐赳赳译).中国社会科学出版社. 2002.
[Williams and Reiter, 2003] Sandra Williams and Ehud Reiter. A corpus analysis of discourse relations for natural language generation. In Proceedings of Corpus Linguistics, 2003.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. A response to Marcu (2003). Discourse structure: trees or graphs? Unpublished manuscript, MIT, Cambridge, MA. 2004.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. Paragraph-, word-, and coherence-based approaches to sentence ranking: A comparison of algorithm and human performance, Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics. Barcelona, Spain. 2004.
[Wolf and Gibson, 2004] F. Wolf and E. Gibson. Representing discourse coherence: A corpus-based analysis, Proceedings of the 20th International Conference on Computational Linguistics (COLING). Geneva, Switzerland. 2004.
[Yue and Feng, 2005] Findings in a Preliminary Study on the Rhetorical Structure of Chinese TV News, Proceedings of 1st Conference of Systemic Functional Grammar (CFSG05), Pp. 29-38. Sydney Australia. July 2005.
[Yue, 2006] Discursive Usage of Six Chinese Punctuation Marks. In Proceedings of COLING/ACL-2006 Student Research Workshop. Sydney Australia. July 2006.
[Zhu,2003] Zhu Yunxia (2003). Incorporating Persuasive Orientations into the Cross-Cultural Study of Genres. Web Proceedings of“Knowledge & Discourse: Speculating on Disciplinary Futures”, 2nd International Conference, Hong Kong. June 2002.
[曹,1995] 曹逢甫。《主题在汉语中的功能研究》(谢天蔚译)。1995。语文出版社。
[陈,2004] 陈群秀。信息处理用现代汉语虚词义类词典研究和工作单设计。《新加坡会议论文集》。 2004 年 7 月。
[陈、邱,1997] 陈忠华、邱国旺。修辞结构理论与修辞结构分析评介。《外语研究》。1997 年 03 期
[戴、薛,2004] 戴炜华、薛雁。修辞体裁分析和修辞结构论。《外语教学》。2004 年第3 期。
[邓,2004] 邓瑜。新闻评论界说新探。我写传媒网 2004-5-28 发布。
[丁,1997] 丁法章(主编)。《新闻评论学》。复旦大学出版社。1997。
[范,1998] 范荣康。《新闻评论学》。人民日报出版社。1988。
[方,2002] 方梅。指示词这和那在北京话中的语法化。《中国语文》2002 年第 4 期。
[冯,2004] 冯光武。汉语语用标记的语义、语用分析,《现代外语》2004 年第 1 期。
[冯,1996] 冯志伟。《自然语言的计算机处理》。上海:上海外语教育出版社。1996。
[冯,1999] 冯志伟。《现代语言学流派》。陕西人民出版社。1999。
[高,1986b] 高名凯。《汉语语法论》。商务印书馆。1986。
[高等,2000] 高维君、姚天顺、黎邦洋、陈伟光、邹嘉彦。机器学习在汉语关联词语识别中的应用。《中文信息学报》。第 14 卷第 3 期,第 1-8 页。2000。
[龚,2000] 龚千炎。《中国语法学史》。语文出版社。2000。
[郭,1999] 郭志良。《现代汉语转折词语研究》。北京语言文化大学出版社。1999。
[郭等,1994] 郭志林等。《应用写作手册》。吉林大学出版社。1994。
[郭等,2003] 郭忠伟、徐延勇、周献中。基于 Schema 和 RST 的自然语言生成混合规划方法。《计算机工程》。2003 年 06 期。
[郝,1983] 郝长留。《语段知识》。语文出版社。1983。
[胡,1996] 胡裕树(主编)。《现代汉语(重订本)》。上海:上海教育出版社。1996。
[胡等,1998] 胡文龙、秦珪、涂光晋。《新闻评论教程》。中国人民大学出版社。1998。
[胡,1994] 胡壮麟(编著)。《语篇的衔接与连贯》。上海:上海外语教育。1994。
[胡,2000] 胡壮麟。《功能主义纵横谈》。北京:外语教学与研究出版社。2000。
[黄,1988] 黄国文(编著)。《语篇分析概要》。湖南教育出版社。1988。
[黄,2001] 黄大网。话语标记研究综述。《福建外语》。2001 年第 1 期。
[黄、李,2002] 黄昌宁、李涓子。《语料库语言学》。商务印书馆。2002。
[黄、廖,2001] 黄伯荣、廖序东(主编)。《现代汉语》(增订二版)。高等教育出版社。2001。
[兰,2002] 兰宾汉。《汉语语法分析的理论与实践》。中国社会科学出版社。2002。 汉语财经评论的修辞结构标注及篇章分析
[黎,1924/2000] 黎锦熙。《新著国语文法》。商务印书馆。1924/2000。
[黎、刘,1962] 黎锦熙、刘世儒。《汉语语法教材》商务印书馆。1962。
[李,1997] 李宇明。汉语语法“本位”论评——兼评邢福义“小句中枢说”。《世界汉语教学》。1:16~23。1997。
[梁,2002] 梁敬美。“这_”和“那_”研究。中国社会科学院博士论文。2002。
[廖,1992] 廖秋忠。《廖秋忠文集》。北京语言学院出版社。1992。
[林,1987] 林裕文。《偏正复句》。《汉语知识讲话》(合订本 5)。上海教育出版社。1987。
[林,2000] 林穗芳。《标点符号学习与应用》。人民出版社。2000。
[刘,1997] 刘挺、吴岩、王开铸。基于信息抽取和文本生成的自动文摘系统设计。《情报学报》。1997 年 1 期。
[刘,2003] 刘世铸、张征。修辞结构理论与 RST 工具。《外语电化教学》。2003 年 4 期
[刘,2005]人民日报经济新闻版主编刘磊访谈实录。 www.people.com.cn。
[陆、马,1985] 陆俭明、马真。《现代汉语虚词散论》。北京大学。1985。
[陆、沈,2003] 陆俭明、沈阳。《汉语和汉语研究十五讲》。北京大学出版社。2003。
[吕,1942/1882] 吕叔湘。《中国文法要略》。商务印书馆。1982。
[吕,1979] 吕叔湘。《汉语语法论文集(增订本)》。商务印书馆。1984。
[吕,1999] 吕叔湘(主编)。《现代汉语八百词(增订本)》。商务印书馆。1999。
[吕,1983] 吕冀平。《汉语语法基础》。黑龙江人民出版社。1983。
[马,1898/2002] 马建忠。《马氏文通》。商务印书馆。1898/2002。
[马,2003] 马广惠。国外对比修辞研究 36 年述评。《山东外语教学》。2003 年 03 期
[梅,1996] 梅汉成。现代汉语句群研究概述。《盐城师专学报(哲社版)》。1996 年第03 期。
[聂,2003] 聂仁发。《现代汉语语篇研究》。湖南师范大学博士论文。2003 年 9 月。
[邵,2001] 邵敬敏。《现代汉语通论》。上海教育出版社。2001。
[沈,1987] 沈开木。《句段分析》。语文出版社。1987。
[苏,1999] 苏培成。《标点符号实用手册》。语文出版社。1999。
[涂,1998] 涂光晋。《广播电视评论学》。新华出版社。1998。
[王,1943] 王力。《中国现代语法》(1943)。《王力文集》(第二卷)重印。山东教育出版社。1985。
[王,1994] 王福祥。《话语语言学概论》。外语教学与研究出版社。1994。
[王,1994] 王伟。“修辞结构理论”评介(上)。《国外语言学》。1994 年第 4 期。
[王,1995] 王伟。“修辞结构理论”评介(下)。《国外语言学》。 1995 年第 2 期。
[王,1997] 王振业。《广播电视新闻评论》。北京广播学院出版社。1997。
[王,2001] 王一禾。2001。 符号小,学问大——写在《标点符号学习与应用》重印之际。 http://www。epsalon。com/printpage。asp?ArticleID=957
[王,2001] 王水莲。修辞结构理论与 AND 结构的语篇功能,《外语与外语教学》。2001年 03 期
[王、白,1989] 王福祥、白春仁 (主编)。《话语语言学论文集》。外语教学与研究出版社。1989。
[王、董,1995] 王伟、董冀平。修辞结构理论与系统功能语言学──两种功能语言理论比较。《山东外语教学》。1995 年 02 期。
[王、胡,2000] 王振业、胡平。2000。《新闻评论写作教程》。中国广播电视出版社。
[王等,1994] 王维贤、张学成、卢曼云、程怀友。《现代汉语复句新解》。 1994。华东师范大学出版社。
[吴,1993] 吴为章。《实用语法修辞》。北京广播学院出版社。1993。
[吴,1997] 吴为章。《广播电视话语研究选集》。北京广播学院出版社。1997。
[吴,2001] 吴启主。《汉语构件语篇学》。岳麓书社。2001。
[吴、田,2000] 吴为章,田小琳。《汉语句群》。商务印书馆。2000。
[夏,2003] 夏蓉。从修辞结构理论看前指在篇章中的分布。《外语与外语教学》。2003年 10 期。
[肖,2003] 肖莉。近百年中国新闻评论得失谈。复旦大学硕士论文。2003。
[邢,2000] 邢福义。《汉语语法学》,东北师范大学出版社。2000。
[邢,2002] 邢福义。《汉语复句研究》。商务印书馆。2002。
[徐,1995] 徐赳赳。话语分析二十年。《外语教学与研究》。1995 年第 1 期。
[徐,1997] 徐赳赳。话语分析在中国。《外语教学与研究》。1997 年第 4 期:20-24。
[徐,2003] 徐赳赳。《现代汉语篇章回指研究》。中国社会科学出版社。2003。
[徐、Webster,1999] 徐赳赳、J. Webster。复句研究与修辞结构理论。《外语教学与研究》,1999。4 :16-22。
[许,2005] 许家金。《青少年汉语口语中话语标记的话语功能研究》。北京外国语大学博士学位论文。2005 年 10 月。
[许,2004] 许余龙。《篇章回指的功能语用探索》。上海:上海外语教育出版社。2004。
[杨,2004] 杨坚定、钟莉莉。动态翻译单位探讨。《中国翻译》。2004 年 05 期。
[姚等,2002] 姚天顺、朱靖波、张俐、杨莹。《自然语言理解—一种让机器懂得人类语言的研究(第二版)》。清华大学出版社,2002。
[尹,2004] 尹汉生。论新闻评论发展趋势。《求索》2004。10
[袁等,1994] 袁晖(主编)。《标点符号词典》。山西人民出版社。1994。
[张,1959] 张志公。《汉语知识》人民教育出版社。1959。
[张,1985] 张寿康。《文章学导论》,湖北教育出版社。1985。
[张, 2000] 张益民。基于混合方法的中文文本解释研究。上海交通大学博士论文。1998。
[张,2000a] 张益民、陆汝占、沈李斌。一种混合型的汉语篇章结构自动分析方法。《软件学报》。2000 年 11 期。
[张,2004] 张德禄。系统功能语言学的新发展。《当代语言学》2004 年第一期:57—65。
[周,2002] 周刚。《连词与相关问题》。安徽教育出版社。2002。
[周,2003a] 周强。中文树库标注规范。《中文信息学报》。 18 (4):1-8。2004。
[周,2003b] 周静。《现代汉语递进范畴研究》。华东师范大学博士论文。
[朱,2004] 朱昆仑。修辞结构理论在大学英语阅读教学中的应用。《山东外语教学》。2004 年 02 期。
[朱,1993] 朱永生(主编)。《语言?语篇?语境:第二届全国系统功能语法研讨会论文集》。北京:清华大学出版社。1993。
[朱等,2002] 朱永生、郑立信、苗兴伟。《英汉语篇衔接手段对比研究》。上海外语教育出版社。2002。
[佐藤,1996] 佐藤一郎。《中国文章论》(赵善嘉译)。上海古籍出版社。1996。