问题生成旨在理解输入端的语义,从而自动生成疑问句。该文主要解决目标答案可知的问题生成任务,输入为陈述句和目标答案,输出为疑问句,该疑问句的答案为给定的目标答案。为了提高问题类型的准确率,使问句的表述更确切,该文提出一种融合问题类型及惩罚机制的问题生成模型,首先使用预训练BERT模型对问题类型进行分类,得到对应问题类型的表示。在编码端,通过门控机制将源端陈述句与问题类型进行融合,得到具有问题类型信息的源端表示。此外,在现有工作中观测到生成的问句和目标答案存在重复词的现象。为了缓解上述问题,该文提出一种惩罚机制,即在损失函数中加入对重复词的惩罚。实验证明,该文所提方法有效提高了问题类型的准确率,并在一定程度上降低了生成重复词的情况。在SQuAD数据集上BLEU-4值达到18.52%,问题类型的准确率达到93.46%。
Abstract
Question Generation aims to understand the semantics of the input and generate questions automatically. This paper focuses on answer-aware question generation, i.e. the input sentence is the target answer of the generated question. We propose a question generation model which integrates the question type and a penalty mechanism. We first fine-tune a pre-trained model BERT to get a question type classifier. Then we use the gate mechanism in the encoder to fuse the source representation and question type information, and obtain the question-type-aware representation. In addition, to alleviate the repeated words in the generated question, we propose a penalty mechanism of generating word from the target answer into the loss. Experimental results show the proposed method can effectively improve the accuracy of question type, and reduce the generated words from target answer to a certain extent. In the SQuAD dataset, the BLEU-4 achieves 18.52%, and the accuracy of question type reaches 93.46%.
关键词
问题生成 /
问题类型 /
惩罚机制
{{custom_keyword}} /
Key words
question generation /
question type /
penalty mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 郑实福,刘挺,秦兵,等.自动问答综述[J].中文信息学报,2002,16(6): 46-52.
[2] 李舟军,李水华. 基于 Web 的问答系统综述[J]. 计算机科学,2017,44(6): 1-7.
[3] Rajpurkar P, Zhang J, Lopyrev K, et al.SQuAD: 100,000+questions for machine comprehension of text[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016: 2383-2392.
[4] Du X, Shao J, Cardie C. Learning to ask: Neural question generation for reading comprehension[J/OL]. arXiv preprint arXiv: 1705.00106, 2017.
[5] Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[J/OL]. arXiv preprint arXiv: 1810.04805, 2018.
[6] Lindberg D, Popowich F, Nesbit J, et al. Generating natural language questions to support learning on-line.[C]//Proceedings of the 14th European Workshop on Natural Language Generation, 2013: 105-114.
[7] Heilman M, Smith N A. Good question! statistical ranking for question generation[C]//Proceedings of the 2010 Annual Conference of the North Amerncan Chapter of the Association for Computational Linguistics, 2010: 609-617.
[8] Scialom T, Piwowarski B, Staiano J. Self-attention architectures for answer-agnostic neural question generation[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019: 6027-6032.
[9] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conterence on Neural Information Processing Systems, 2017: 5998-6008.
[10] Zhou Q, Yang N, Wei F, et al. Neural question generation from text: A preliminary study[C]//Proceedings of National CCF Conference on Natural Language Processing and Chinese Computing. Springer, Cham, 2017: 662-671.
[11] Gulcehre C, Ahn S, Nallapati R, et al. Pointing the unknown words[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(ACL), 2016: 140-149.
[12] Dong X, Hong Y, Chen X, et al.Neural question generation with semantics of question type[C]//Proceedings of CCF International Conference on Natural Language Processing and Chinese Computing. Springer, Cham, 2018: 213-223.
[13] Zhou W, Zhang M, Wu Y. Multi-task learning with language modeling for question generation[J/OL]. arXiv preprint arXiv: 1908.11813, 2019.
[14] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[15] Bahdanau Dzmitry, Cho Kyunghyun, Bengio Yoshua. Neural machine translation by jointly learning to align and translate[J/OL]. arXiv preprint arXiv: 1409.0473,2014.
[16] See A, Liu P, Manning D.Get to the point: Summarization with pointer-generator networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics(ACL), 2017: 1073-1083.
[17] Pennington J, Socher R, Manning C. Glove: Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014: 1532-1543.
[18] Kingma, Diederik P, Jimmy Ba. Adam: A method for stochastic optimization[J/OL]. arXiv preprint arXiv: 1412.6980,2014.
[19] Papineni K, Roukos S, Ward T, et al. BLEU: a method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2002: 311-318.
[20] Denkowski M, Lavie A. Meteor universal: Language specific translation evaluation for any target language[C]//Proceedings of the 9th Workshop on Statistical Machine Translation, 2014: 376-380.
[21] Lin C Y. Rouge: A package for automatic evaluation of summaries[C]//Proceedings of Post-conterence Worksshop on Text Summarization Branches Out, ALL, 2004:74-81.
[22] Chen X, Fang H, Lin T, et al. Microsoft COCO captions: Data collection and evaluation server[J/OL]. arXiv preprint arXiv: 1504.00325,2015.
[23] Song L, Wang Z, Hamza W, et al. Leveraging context information for natural question generation[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2018: 569-574.
[24] Zhao Y, Ni X, Ding Y, et al. Paragraph-level neural question generation with maxout pointer and gated self-attention networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing,2018: 3901-3910.
[25] Kim Y, Lee H, Shin J, et al. Improving neural question generation using answer separation[J/OL]. arXiv preprint arXiv: 1809.02393,2018.
[26] Wu K, Hong Y, Zhu M, et al. Separate answer decoding for multi-class question generation[C]//Proceedings of the 2019 International Conference on Asian Langnage Processing, 2019:325-330.
[27] Qiu J, Xiong D. Generating highly relevant questions[J/OL]. arXiv preprint arXiv: 1910.03401, 2019.
[28] Zhang S, Bansal M. Addressing semantic drift in question generation for semi-supervised question answering[J/OL]. arXiv preprint arXiv: 1909.06356, 2019.
[29] Fellbaum C. WordNet an electronic lexical database[M]. MA:MITPress,1998.
[30] Dror R, Baumer G, Shlomov S, et al. The hitchhiker’s guide to testing statistical significance in natural language processing[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1383-1392.
[31] Johnson D H. The insignificance of statistical significance testing[J]. The Journal of Wildlife Management, 1999,63: 763-772.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
科技部重点研发项目(2017YFB1002104)
{{custom_fund}}
PDF(1799 KB)
