复述识别任务,即判断两个句子是否表达相同的语义。传统的复述识别任务针对的是通用领域,模型通过理解两个句子的语义,比较句子的语义相似度从而进行复述判断。而在特定领域的复述识别任务中,模型必须结合该领域的专业知识,才能准确地理解两个句子的语义,并进一步判断出它们的区别与联系。该文针对特定领域提出了一种基于领域知识融合的复述识别方法。方法首先为句子检索专业知识,再将专业知识融入到每个句子的语义中,最后实现更准确的语义相似度判断。该文在计算机科学领域的复述识别数据集PARADE上进行了相关实验,实验结果显示,该文方法在F1指标上达到了73.9,比基线方法提升了3.1。
Abstract
The paraphrase identification is to deciden whether two sentences express the same meaning. It is relatively easy for the general domain paraphrase identification to understand and judge the relationship between two sentences. To improve the paraphrase identification in specific domains, we propose a paraphrase identification method based on domain knowledge fuison. We retrieval the knowledge from the knowledge base and integrated them into the model. Experiments on the PARADE dataset (in computer science domain) show our method has reached 73.9% F1 score, out-performing the baseline by 3.1%.
关键词
复述识别 /
特定领域 /
知识融合
{{custom_keyword}} /
Key words
paraphrase identification /
special domain /
knowledge incorporation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] CHEN Q, ZHU X, LING Z H, et al. Enhanced LSTM for natural language inference[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1657-1668.
[2] RAJPURKAR P, ZHANG J, LOPYREV K, et al. SQuAD: 100,000+ questions for machine comprehension of text[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 2383-2392.
[3] VOORHEES E M. Overview of the TREC 2001 question answering track[C]//Proceedings of the 10th TextREtrieval Conference, 2001.
[4] ALLAM A M N,HAGGAG M H. The question answering systems: A survey[J]. International Journal of Research and Reviews in Information Sciences, 2012, 2(3):1123-1129.
[5] WU Y, SCHUSTER M, CHEN Z, et al. Googles neural machine translation system: Bridging the gap between human and machine translation[J/OL].arXiv preprint arXiv:1609.08144, 2016.
[6] MIKKOLA M, LEMPI J, SNTTI V. Information retrieval system: U.S. Patent 6,529,143[P]. 2003-3-4.
[7] CHEN Z, ZHANG H, ZHANG X, et al. Quora questionpairs[EB/OL]. https://www.kaggle.com/competitions/quora-question-pairs/[2023-02-13].
[8] DOLAN W B, BROCKETT C. Automatically constructing a corpus of sentential paraphrases[C]//Proceedings of the 3rd International Workshop on Paraphrasing, 2005.
[9] HE Y, WANG Z, ZHANG Y, et al. PARADE: A new dataset for paraphrase identification requiring computer science domain knowledge[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 7572-7582.
[10] LIU X, CHEN Q, DENG C, et al. LCQMC: A large-scale chinese question matching corpus[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018: 1952-1962.
[11] SEVERYN A, MOSCHITTI A. Learning to rank short text pairs with convolutional deep neural networks[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015: 373-382.
[12] WANG Z, HAMZA W, FLORIAN R. Bilateral multi-perspective matching for natural language sentences[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017: 4144-4150.
[13] PANG L, LAN Y, GUO J, et al. Text matching as image recognition[C]//Proceedings of the AAAI Conference onArtificial Intelligence, 2016:2793-2799.
[14] PARIKH A,TCKSTRM O, DAS D, et al. A decomposable attention model for natural language inference[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 2249-2255.
[15] GONG Y, LUO H, ZHANG J. Natural language inference over interaction space[J/OL].arXiv preprint arXiv:1709.04348, 2017.
[16] KENTON J D M W C, TOUTANOVA L K. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of NAACL-HLT, 2019: 4171-4186.
[17] GANITKEVITCH J, VAN DURME B, CALLISON-BURCH C. PPDB: The paraphrase database[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2013: 758-764.
[18] SPEER R, CHIN J,HAVASI C. Conceptnet 5.5: An open multilingual graph of general knowledge[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2017: 4444-4451.
[19] CHEN Q, ZHU X, LING Z H, et al. Neural natural language inference models enhanced with external knowledge[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 2406-2417.
[20] KILGARRIFF A. Wordnet: An electronic lexical database[M/OL]. 1998. https://books.google.com/books[2023-02-13].
[21] XU Y, ZHU C, XU R, et al. Fusing contextinto knowledge graph for commonsense question answering[C]//Proceedings of the Association for Computational Linguistics, 2021: 1201-1207.
[22] MEYER C M,GUREVYCH I. Wiktionary: A new rival for expert-built lexicons? exploring the possibilities of collaborative lexicography[M/OL]. https://download.hrz.tu-darmstadt.de/media/FB20/Dekanat/Publikationen/UKP/oup-elex2012-meyer-wiktionary.pdf[2023-02-13].
[23] WIKIMEDIA. Wikipedia[EB/OL].http://wikipedia.org/[2021-05-20].
[24] KIM S, KANG I, KWAK N. Semantic sentence matching with densely-connected recurrent and co-attentiveinforma-tion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(01): 6586-6593.
[25] CHEN Q, ZHU X, LING Z H, et al. Enhanced LSTM for natural language inference[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1657-1668.
[26] HE H, LIN J. Pairwise word interaction modeling with deep neural networks for semantic similarity measurement[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016: 937-948.
[27] NIE Y, BANSAL M. Shortcut-stacked sentence encoders for multi-domain inference[C]//Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP, 2017: 41-45.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研发计划项目(2017YFB1002104)
{{custom_fund}}
PDF(1628 KB)
