[1]方昱龙,王泽锦,王华珍,等.基于模板学习的智能侨情问句生成方法[J].华侨大学学报(自然科学版),2023,44(6):735-742.[doi:10.11830/ISSN.1000-5013.202304010]
　FANG Yulong,WANG Zejin,WANG Huazhen,et al.Intelligent Question Generation Method Based on Template Learning for Overseas Chinese Situation[J].Journal of Huaqiao University(Natural Science),2023,44(6):735-742.[doi:10.11830/ISSN.1000-5013.202304010]
点击复制

基于模板学习的智能侨情问句生成方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第44卷
期数:
2023年第6期
页码:
735-742
栏目:
出版日期:
2023-11-20

文章信息/Info

Title:
Intelligent Question Generation Method Based on Template Learning for Overseas Chinese Situation
文章编号:
1000-5013(2023)06-0735-08
作者:
方昱龙;  王泽锦;  王华珍;  何霆
华侨大学 计算机科学与技术学院, 福建 厦门 361021
Author(s):
FANG Yulong;  WANG Zejin;  WANG Huazhen;  HE Ting
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
关键词:
侨情;  问句生成;  模板学习;  seq2seq;  注意力机制
Keywords:
overseas Chinese situation;  question generation;  template learning;  seq2seq;  attention mechanism
分类号:
TP394.4
DOI:
10.11830/ISSN.1000-5013.202304010
文献标志码:
A
摘要:
为解决侨情问句甚少导致训练的侨情语料较少的问题,提出一种基于模板学习的智能侨情问句生成方法。首先,对侨情篇章文本进行包含主题、关系、对象的三元组抽取;其次,构建训练数据集,输入数据由主题和关系构成,输出数据为问句模板;随后,采用以BERT+LSTM+Attention为核心算法的seq2seq框架,实现问句模板生成;最后,对模板问句进行主题文本替换,从而得到最终的实例化问句。采用BLEU,ROUGE-N,公开问答系统评测及人工评价方式对文中方法进行评价。结果表明:BLEU,ROUGE-N,公开问答系统评测及人工评价方式对文中方法的评测结果分别为0.77,0.67,81%,88%,较基线模型有较大的提升。
Abstract:
To address the issue of limited training for overseas Chinese language materials due to the scarcity of overseas Chinese question sentences, a template learning based intelligent overseas Chinese situation generation method is proposed. Firstly, the text of overseas Chinese situation is extracted by triplet including theme, relationship and object. Secondly, the training data set is constructed, its input data are composed of themes and relationships, and its output data is question template. Then, BERT+LSTM+Attention as the core algorithm of seq2seq framework is applied to generate question template. Finally, the template question is replaced by the theme text to get the final instantiated question. BLEU, ROUGE-N, public question answering system evaluation and human evaluation method were used to evaluate the proposed method. The results show that the evaluation results of the BLEU, ROUGE-N, public question answering system evaluation and human evaluation method are 0.77, 0.67, 81% and 88%, respectively, with significant improvements compared to the baseline model.

参考文献/References:

[1] RUS V,WYSE B,PIWEK P,et al.The first question generation shared task evaluation challenge[C]//Proceedings of the 6th International Natural Language Generation Conference.Trim Castle:School of Computer Science and Statistics,2010:7-9.DOI:10.5555/2187681.2187740.
[2] HEILMAN M,SMITH N A.Extracting simplified statements for factual question generation[C]//Proceedings of QG 2010: The Third Workshop on Question Generation.Pittsburgh:Springer-Verlag,2010:11-20.
[3] ALI H,CHALI Y,HASAN S A.Automatic question generation from sentences[C]//In Actes de la 17e Conférence sur le Traitement Automatique des Langues Naturelles.Montréal:Université de Montréal,2010:213-218.
[4] MANNEM P,PRASAD R,JOSHI A.Question generation from paragraphs at UPenn: QGSTEC system description[C]//Proceedings of QG 2010:The Third Workshop on Question Generation.Pittsburgh:Springer-Verlag,2010:84-91.
[5] SHANTHI BALA P,AGHILA G.Q-genesis: Question generation system based on semantic relationships[C]//Proceedings of ICBDCC18.Coimbatore:Springer,2019:509-517.DOI:10.1007/978-981-13-1882-5_44.
[6] KWATE DASSI L.Semantic-based self-critical training for question generation[EB/OL].(2021-08-26)[2023-04-10] .https://doi.org/10.48550/arXiv.2108.12026.
[7] DIVATE M,SALGAONKAR A.Automatic question generation approaches and evaluation techniques[J].Current Science,2017,113(9):1683-1691.DOI:10.18520/cs/v113/i09/1683-1691.
[8] CURTO S,MENDES A C,COHEUR L.Question generation based on lexico-syntactic patterns learned from the web[J].Dialogue and Discourse,2012,3(2):147-175.DOI:10.5087/dad.2012.207.
[9] 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.Sofia:Association for Computational Linguistics,2013:105-114.
[10] CHALI Y,GOLESTANIRAD S.Ranking automatically generated questions using common human queries[C]//International Natural Language Generation Conference.Edinburgh:Association for Computational Linguistics,2016:217-221.DOI:10.18653/v1/W16-6635.
[11] WANG Liuyin,XU Zihan,LIN Zibo,et al.Answer-driven deep question generation based on reinforcement learning[C]//Proceedings of the 28th International Conference on Computational Linguistics.Barcelona:Association for Computational Linguistics,2020:5159-5170.DOI:10.18653/v1/2020.coling-main.452.
[12] DU Xinya,SHAO Junru,CARDIE C.Learning to ask: Neural question generation for reading comprehension[EB/OL].(2017-04-29)[2023-03-19] .https://doi.org/10.48550/arXiv.1705.00106.
[13] ZHOU Qingyu,YANG Nan,WEI Furu,et al.Neural question generation from text: A preliminary study[C]//National CCF Conference on Natural Language Processing and Chinese Computing.Cham:Springer,2017:662-671.DOI:10.1007/978-3-319-73618-1_56.
[14] YUAN Xingdi,WANG Tong,GULCEHRE C,et al.Machine comprehension by text-to-text neural question generation[C]//Proceedings of the 2nd Workshop on Representation Learning for NLP.Vancouver:Association for Computational Linguistics,2017:15-25.DOI:10.18653/v1/W17-2603.
[15] LIU Tianyu,WEI Bingzhen,CHANG Baobao,et al.Large-scale simple question generation by template-based seq2seq learning[C]//National CCF Conference on Natural Language Processing and Chinese Computing.Cham:Springer,2017:75-87.DOI:10.1007/978-3-319-73618-1_7.
[16] TUAN L A,SHAH D,BARZILAY R.Capturing greater context for question generation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.New York:AAAI Press,2020:9065-9072.DOI:10.1609/aaai.v34i05.6440.
[17] DEVLIN J,CHANG Mingwei,LEE K,et al.BERT: Pre-training of deep bidirectional transformers for language understanding[EB/OL].(2018-10-11)[2023-03-19] .https://doi.org/10.48550/arXiv.1810.04805.
[18] CHO K,MERRIENBOER B V,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.Doha:ACL,2014:1724-1734.DOI:10.3115/v1/D14-1179.
[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.Philadelphia:ACL,2002:311-318.DOI:10.3115/1073083.1073135.
[20] LIN C Y.Rouge: A package for automatic evaluation of summaries[C]//Proceedings of the Workshop on Text Summarization Branches Out(WAS 2004).Barcelona:ACL,2004:74-81.
[21] WERBOS P J.Generalization of backpropagation with application to a recurrent gas market mode[J].Neural Networks,1988,1(4):339-356.DOI:10.1016/0893-6080(88)90007-X.
[22] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[23] SCHUSTER M,PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.DOI:10.1109/78.650093.

备注/Memo

备注/Memo:
收稿日期: 2023-04-18
通信作者: 王华珍(1975-),女,副教授,博士,主要从事人工智能、机器学习、增强现实、虚拟现实等的研究。E-mail:wanghuazhen@hqu.edu.cn。
基金项目: 国家重点研发计划项目(2018YFB1402500); 教育部中外语言交流合作中心国际中文教育研究课题(21YH30B); 福建省社会科学基金资助项目(FJ2021B110); 中央高校基本科研业务费自主项目(TZYB-202005);
更新日期/Last Update: 2023-11-20