省略作为一种常见的语言现象,在上下文中普遍存在,特别是在问答、对话等短文本中出现的频率更高。不同于传统的机器学习方法,该文针对问答、对话这样的短文本,构建了一个序列到序列的神经网络模型来实现对上下文中出现的省略进行识别和补全。在搜集和整理的短文本问答和对话语料上进行了各种实验,验证了该模型在省略识别和恢复上能够取得较好的性能。
Abstract
Ellipsis is a common linguistic phenomenon, which is ubiquitous especially in short texts such as QA and dialogue. This paper builds a sequence-to-sequence neural network model for short texts to identify and recover ellipsis. Various experiments are conducted on the collected and sorted short text corpus for QA and dialogue, demonstrating good performances of the proposed model ellipsis identification and recovery.
关键词
序列到序列 /
对话 /
省略
{{custom_keyword}} /
Key words
sequence to sequence /
dialogue /
ellipsis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Kim Y J. Subject/object drop in the acquisition of Korean:A cross-linguistic comparison[J]. Journal of East Asian Linguistics,2000,9(4):325-351.
[2] Sutskever I,Vinyals O,Le Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the Advances in Neural Information Processing Systems. 2014:3104-3112.
[3] Mary Dalrymple,Stuart M Shieber,Fernando C N Pereira. Ellipsis and higher-order unification[J]. Linguistics and Philosophy,1991,14(4):399-452.
[4] Shieber S M,Fernando C N,Dalrymple M. Interactions of scope and ellipsis[J]. Linguistics and Philosophy,1996,19(5):527-552.
[5] Nielsen L A. A corpus-based study of verb phrase ellipsis [C]//Proceedings of the 6th Annual Cluk Research Colloquium,2003:109-115.
[6] Liu Z,Pellicer E G,Gillick D. Exploring the steps of verb phrase ellipsis[C]//Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016). 2016:32-40.
[7] Kong F,Zhou G. A tree kernel-based unified framework for Chinese zero anaphora resolution[C]//Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics,2010:882-891.
[8] Fang K,Guodong Z. Chinese zero pronoun resolution:A chain to chain approach[C]//Proceedings of the National CCF Conference on Natural Language Processing and Chinese Computing. Springer,Cham,2017:393-405.
[9] Chen C,Ng V. Chinese zero pronoun resolution with deep neural networks[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). 2016,1:778-788.
[10] Chen C,Ng V. Chinese zero pronoun resolution:An unsupervised probabilistic model rivaling supervised resolvers[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014:763-774.
[11] Chen C,Ng V. Chinese zero pronoun resolution:An unsupervised approach combining ranking and integer linear programming[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence. 2014:1622-1628.
[12] Cai S,Chiang D,Goldberg Y. Language-independent parsing with empty elements[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies:short papers-Volume 2. Association for Computational Linguistics,2011:212-216.
[13] Kong F,Zhou G. A clause-level hybrid approach to Chinese empty element recovery[C]//Proceedings of the 23rd IJCAI. 2013:2113-2119.
[14] Xue N,Yang Y. Dependency-based empty category detection via phrase structure trees[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. 2013:1051-1060.
[15] Huang Y,et al. A theme structure method for the ellipsis resolution[C]//Proceedings of the 7th European Conference on Speech Communication and Technology,2001.
[16] 尹庆宇,等.省略识别及恢复联合模型研究[J]. 计算机研究与发展,2015,52(11):2460-2467.
[17] Kumar V,Joshi S. Non-sentential question resolution using sequence to sequence learning[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers. 2016:2022-2031.
[18] Hochreiter S,Schmidhuber J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[19] M Schuster,K Paliwal,Bidirectional re-current neural networks[J]. IEEE Transactions on Signal Processing,1997,45(11):2673-2681.
[20] Bahdanau D,Cho K,Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473,2014.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61472264);人工智能应急项目(61751206);国家重点研发计划子课题(2017YFB1002101); 国家自然科学基金(61502149)
{{custom_fund}}
PDF(2797 KB)
