创新构想话题生成
|
摘要
文章提出了创新构想话题的自动生成任务,主动生成具有新颖性、权威性的话题,能够激发群体讨论热情,有助于推动相关领域的发展。以Encoder-Decoder文本生成技术为基础,构建了一套创新构想话题生成框架。首先通过实时爬取相关网站的内容,作为信息获取的主要来源;然后利用数据分析工具提取文本的关键词和摘要,使用了TF-IDF算法和TextRank算法;最后利用训练好的话题生成模型得到话题表达。实验结果展示了生成的创新构想话题,说明基于该文提出的流程可以有效挖掘文档中潜在的话题。
This paper introduces the automatic generation task of creative concept topic,creating a topic of novelty and authority that can stimulate discussion enthusiasm of the group and have the potential to promote the development of the related fields.Based on Encoder-Decoder text generation technology,this paper constructs a framework for the generation of creative concept topic.The content of the related websites is crawled in real time as the main source of information acquisition,the key words and abstracts of the text are extracted with the data analysis tool by using TF-IDF algorithm and TextRank algorithm,and the topic expression is obtained by using the trained topic generation model.The experimental results show that the generated topic of creative concept is presented,which shows that the process proposed in this paper can effectively extract potential topics in documents.
This paper introduces the automatic generation task of creative concept topic,creating a topic of novelty and authority that can stimulate discussion enthusiasm of the group and have the potential to promote the development of the related fields.Based on Encoder-Decoder text generation technology,this paper constructs a framework for the generation of creative concept topic.The content of the related websites is crawled in real time as the main source of information acquisition,the key words and abstracts of the text are extracted with the data analysis tool by using TF-IDF algorithm and TextRank algorithm,and the topic expression is obtained by using the trained topic generation model.The experimental results show that the generated topic of creative concept is presented,which shows that the process proposed in this paper can effectively extract potential topics in documents.
引文
[1] Mnih V,Kavukcuoglu K,Silver D,et al.Human-Level Control Through Deep Reinforcement Learning[J].Nature,2015,518(7540):529-533.DOI:10.1038/nature14236.
[2] Mihalcea R,Tarau P.Text Rank-Bringing Order into Texts[C]∥Proceedings of the Conference on Empirical Methods in Natural Language Processing,2004:404-411.
[3] Sutskever I,Vinyals O,Le Q V.Sequence to Sequence Learning with Neural Networks[C]∥Advances in Neural Information Processing Systems,2014,4:3104-3112.
[4] Salton G.The SMART Retrieval System-Experiments in Automatic Document Processing[M].Englewood Cliffs,NewJersey:Prentice Hall Inc,1971.
[5] Zhou L,Zheng J,Ge Z,et al.Multimode Process Monitoring Based on Switching Autoregressive Dynamic Latent Variable Model[J].IEEE Transactions on Industrial Electronics,2018,65(10):8184-8194.DOI:10.1109/TIE.2018.2803727.
[6]张瑾,王小磊,许洪波.自动文摘评价方法总述[J].中文信息学报,2008,2(3):81-88.DOI:10.3969/j.issn.1003-0077.2008.03.011.Zhang J,Wang X L,Xu H B.Summary of Automatic Abstraction Evaluation Method[J].Journal of Chinese Information,2008,2(3):81-88.DOI:10.3969/j.issn.1003-0077.2008.03.011.
[7] Hu M,Liu B.Mining and Summarizing Customer Reviews[C]∥Proceedings of SIGKDD04.2004.DOI:10.1145/1014052.1014073.
[8] Gehring J,Auli M,Grangier D,et al.Convolutional Sequence to Sequence Learning[J].Gehring Convolutional,2017,1705:03122.
[9] Weiss R J,Chorowski J,Jaitly N,et al.Sequence-to-Sequence Models Can Directly Translate Foreign Speech[J].2017:2625-2629.
[10] Mikolov T.Word2vec Project[CP/OL].http:∥code.google.com/p/word2vec/.DOI:10.3969/j.issn.1005-6033.2015.02.061.
[11] Mikolov T,Sutskever I,Chen K,et al.Distributed Representations of Words and Phrases and Their Compositionality[C]∥Proceedings of NIPS,2013:3111-3119.
[12] Mikolov T,Chen K,Corrado G,et al.Effcient Estimation of Word Representations in Vector Space[Z/OL].arXiv:1301.3781v3.
[13]陈悦,刘则渊,陈劲,等.科学知识图谱的发展历程[J].科学学研究,2008,26(3):449-460.Chen Y,Liu Z Y,Chen J,et al.The Development of Map of Scientific Knowledge[J].Science Research,2008,26(3):449-460.
[14] Sehgal U,Kaur K,Kumar P.The Anatomy of a Large-scale Hypertextual Web Search Engine[C]∥Second International Conference on Computer&Electrical Engineering.IEEE Computer Society,2009:59.DOI:10.1109/ICCEE.2009.59.
[15] Hollis G,Westbury C,Lefsrud L.Extrapolating Human Judgments from Skip-gram Vector Representations of Word Meaning[J].Quarterly Journal of Experimental Psychology,2017,70(8):1603-1619.DOI:10.1080/17470218.2016.1195417.
[16] Vaswani A,Shazeer N,Parmar N,et al.Attention is All You Need[C]∥31st Conference on Neural Information Processing Systems(NIPS 2017),2017:5998-6008.
[17] Newey W K.Adaptive Estimation of Regression Models via Moment Restrictions[J].Journal of Econometrics,1988,38(3):301-339.DOI:10.1016/0304-4076(88)90048-6.
(1)原文链接:http://tech.163.com/17/1118/08/D3GSVLN000097U7R.html
[2] Mihalcea R,Tarau P.Text Rank-Bringing Order into Texts[C]∥Proceedings of the Conference on Empirical Methods in Natural Language Processing,2004:404-411.
[3] Sutskever I,Vinyals O,Le Q V.Sequence to Sequence Learning with Neural Networks[C]∥Advances in Neural Information Processing Systems,2014,4:3104-3112.
[4] Salton G.The SMART Retrieval System-Experiments in Automatic Document Processing[M].Englewood Cliffs,NewJersey:Prentice Hall Inc,1971.
[5] Zhou L,Zheng J,Ge Z,et al.Multimode Process Monitoring Based on Switching Autoregressive Dynamic Latent Variable Model[J].IEEE Transactions on Industrial Electronics,2018,65(10):8184-8194.DOI:10.1109/TIE.2018.2803727.
[6]张瑾,王小磊,许洪波.自动文摘评价方法总述[J].中文信息学报,2008,2(3):81-88.DOI:10.3969/j.issn.1003-0077.2008.03.011.Zhang J,Wang X L,Xu H B.Summary of Automatic Abstraction Evaluation Method[J].Journal of Chinese Information,2008,2(3):81-88.DOI:10.3969/j.issn.1003-0077.2008.03.011.
[7] Hu M,Liu B.Mining and Summarizing Customer Reviews[C]∥Proceedings of SIGKDD04.2004.DOI:10.1145/1014052.1014073.
[8] Gehring J,Auli M,Grangier D,et al.Convolutional Sequence to Sequence Learning[J].Gehring Convolutional,2017,1705:03122.
[9] Weiss R J,Chorowski J,Jaitly N,et al.Sequence-to-Sequence Models Can Directly Translate Foreign Speech[J].2017:2625-2629.
[10] Mikolov T.Word2vec Project[CP/OL].http:∥code.google.com/p/word2vec/.DOI:10.3969/j.issn.1005-6033.2015.02.061.
[11] Mikolov T,Sutskever I,Chen K,et al.Distributed Representations of Words and Phrases and Their Compositionality[C]∥Proceedings of NIPS,2013:3111-3119.
[12] Mikolov T,Chen K,Corrado G,et al.Effcient Estimation of Word Representations in Vector Space[Z/OL].arXiv:1301.3781v3.
[13]陈悦,刘则渊,陈劲,等.科学知识图谱的发展历程[J].科学学研究,2008,26(3):449-460.Chen Y,Liu Z Y,Chen J,et al.The Development of Map of Scientific Knowledge[J].Science Research,2008,26(3):449-460.
[14] Sehgal U,Kaur K,Kumar P.The Anatomy of a Large-scale Hypertextual Web Search Engine[C]∥Second International Conference on Computer&Electrical Engineering.IEEE Computer Society,2009:59.DOI:10.1109/ICCEE.2009.59.
[15] Hollis G,Westbury C,Lefsrud L.Extrapolating Human Judgments from Skip-gram Vector Representations of Word Meaning[J].Quarterly Journal of Experimental Psychology,2017,70(8):1603-1619.DOI:10.1080/17470218.2016.1195417.
[16] Vaswani A,Shazeer N,Parmar N,et al.Attention is All You Need[C]∥31st Conference on Neural Information Processing Systems(NIPS 2017),2017:5998-6008.
[17] Newey W K.Adaptive Estimation of Regression Models via Moment Restrictions[J].Journal of Econometrics,1988,38(3):301-339.DOI:10.1016/0304-4076(88)90048-6.
(1)原文链接:http://tech.163.com/17/1118/08/D3GSVLN000097U7R.html