摘要
针对语义省略"的"字结构识别任务,提出一种基于组合神经网络的识别方法。利用词语和词性,通过双向LSTM (long short-term memory)神经网络,学习"的"字结构深层次的语义语法表示。通过Max-pooling层和基于GRU (gatedrecurrentunit)的多注意力层,捕获"的"字结构的省略特征,完成语义省略"的"字结构识别任务。实验结果表明,所提模型在CTB8.0 (ChineseTreebank 8.0)语料中,能够有效地识别语义省略的"的"字结构, F1值达到96.67%。
To slove the classification of the "de" structure containing the usage of semantic ellipsis, a hybrid neural network is built. Firstly, the network uses a bidirectional LSTM(long short-term memory) neural network to learn more syntactic and semantic information of the "de" structure. Then, the network employs a Max-pooling layer or GRU(gated recurrent unit) based multiple attention layers to capture features of ellipsis of the "de" structure by which the network can recognize the "de" structure containing the usage of semantic ellipsis. Experiments on CTB8.0 corpus show that the proposed approach can achieve accurate results efficiently, the F1 value is 96.67%.
引文
[1]徐阳春.关于虚词“的”及其相关问题研究[D].上海:复旦大学,2003:48-74
[2]黄国营.“的”字的句法、语义功能.语言研究,1982(1):101-129
[3]吕叔湘.现代汉语八百词.北京:商务印书馆,1980:156-163
[4]孔令达.“名_1+的+名_2”结构中心名词省略的语义规则.安徽师大学报(哲学社会科学版),1992,20(1):103-107
[5]石毓智.论“的”的语法功能的同一性.世界汉语教学,2000(1):16-27
[6]张坤丽,昝红英,柴玉梅,等.现代汉语虚词用法知识库建设综述.中文信息学报,2015,29(3):1-8
[7]韩英杰,昝红英,张坤丽,等.基于规则的现代汉语常用助词用法自动识别.计算机应用,2011,31(12):3271-3274
[8]刘秋慧,张坤丽,许鸿飞,等.助词“的”用法自动识别研究.北京大学学报(自然科学版),2018,54(3):466-474
[9]曲维光,周俊生,吴晓东,等.自然语言句子抽象语义表示AMR研究综述.数据采集与处理,2017,32(1):26-36
[10]李斌,闻媛,卜丽君,等.英汉《小王子》抽象语义图结构的对比分析.中文信息学报,2017,31(1):50-57
[11]李斌,闻媛,宋丽,等.融合概念对齐信息的中文AMR语料库的构建.中文信息学报,2017,31(6):93-102
[12]Mikolov T,Sutskever I,Chen K,et al.Distributed representations of words and phrases and their compositionality//Proceedings of the 27th Annual Conference on Neural Information Processing Systems.Lake Tahoe,2013:3111-3119
[13]Tang D,Qin B,Liu T.Aspect level sentiment classification with deep memory network//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Austin,2016:214-224
[14]Chen P,Sun Z,Bing L,et al.Recurrent attention network on memory for aspect sentiment analysis//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Copenhagen,2017:452-461
[15]Schuster M,Paliwal K K.Bidirectional recurrent neural networks.IEEE Transactions on Signal Processing,1997,45(11):2673-2681
[16]Sachan D S,Zaheer M,Salakhutdinov R.Investigating the working of text classifiers[EB/OL].(2018-01-19)[2018-06-29].https://arxiv.org/abs/1801.06261
[17]Sukhbaatar S,Szlam A,Weston J,et al.End-to-end memory networks//Proceedings of the 28th Annual Conference on Neural Information Processing Systems.Montreal,2015:2440-2448
[18]Kumar A,Irsoy O,Ondruska P,et al.Ask me anything:dynamic memory networks for natural language processing//Proceedings of the 33rd International Conference on Machine Learning.New York City,2016:1378-1387
[19]Chung J,Gulcehre C,Cho K H,et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL].(2014-12-11)[2018-06-29].https://arxiv.org/abs/1412.3555
[20]Conneau A,Kiela D,Schwenk H,et al.Supervised learning of universal sentence representations from natural language inference data//Proceedings of the2017 Conference on Empirical Methods in Natural Language Processing.Copenhagen,2017:670-680
[21]Collobert R,Weston J.A unified architecture for natural language processing:deep neural networks with multitask learning//Proceedings of the 25th International Conference on Machine Learning.Helsinki,2008:160-167
[22]Kingma D P,Ba J.Adam:a method for stochastic optimization[EB/OL].(2014-12-22)[2018-06-29].https://arxiv.org/abs/1412.6980v8
[23]Srivastava N,Hinton G E,Krizhevsky A,et al.Dropout:a simple way to prevent neural networks from overfitting.Journal of Machine Learning Research,2014,15(1):1929-1958