吉宇,王笑月,李茹,郭少茹,关勇. 多模块联合的阅读理解候选句抽取[J]. 中文信息学报, 2022, 36(6): 109-116.
JI Yu, WANG Xiaoyue, LI Ru, GUO Shaoru, GUAN Yong. Evidence Sentence Extraction for Reading Comprehension Based on Multi-module. , 2022, 36(6): 109-116.
Evidence Sentence Extraction for Reading Comprehension Based on Multi-module
JI Yu1, WANG Xiaoyue1, LI Ru1,2, GUO Shaoru1, GUAN Yong1,2
1.School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China; 2.Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan, Shanxi 030006, China
Abstract：In machine reading comprehension, the task of multiple choice reading comprehensioniis challenged by evidence sentence extraction due to the absence of clue annotation and questions involve multi-hop reasoning. This paper proposes a model of evidence sentence extraction based on multi-module combination. We first apply some labeled data to fine-tune the pre-training model. Then the evidence sentences in the multi-hop reasoning problem are extracted recursively through TF-IDF. Finally, the unsupervised method is combined to further filter the model prediction results to reduce redundancy Tested on the Chinese Gaokao and the RACE data set, the proposed method achieves an increase of 3.44% in F1 value compared with the optimal baseline model in evidence sentence extracton. Meanwhile, the final question-answering accuracy with above identified evidence sentences is improved by 3.68% and 3.6%, respectively, compared with that of full text as input.
[1] Mostafazadeh N, Chambers N, He X, et al. A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2016:839-849. [2] Guokun Lai, Qizhe Xie, Hanxiao Liu,et al. RACE: Large-scale reading comprehension dataset from examinations.[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 796-805. [3] Hai W, Yu D, Sun K, et al. Evidence sentence extraction for machine reading comprehension[C]//Proceedings of the 23rd Conference on Computational Natural Language Learning,2019: 696-707. [4] Ran Q, Li P, Hu W, et al. Option comparison network for multiple-choice reading comprehension[J]. arXiv preprint arXiv:1903.03033, 2019. [5] Zhang S, Zhao H, Wu Y, et al. DCMN+: Dual co-matching network for multi-choice reading comprehension[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5):9563-9570. [6] Trivedi H, Kwon H, Khot T, et al. Repurposing entailment for multi-hop question answering tasks[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics, 2019: 2948-2958. [7] Korman D Z, Mack E, Jett J, et al. Defining textual entailment[J]. Journal of the Association for Information Science and Technology, 2018: 763-772. [8] Adina Williams, Nikita Nangia, Samuel Bowman. A broad-coverage challenge corpus for sentence understanding through inference[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics, 2018: 1112-1122. [9] Vikas Yadav, Steven Bethard, Mihai Surdeanu. Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering[C]//Proceedings of the Empirical Methods in Natural Language Processing and theInternational Joint Conference on Natural Language Processing, 2019:2578-2589. [10] Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics,2019:4171-4186. [11] Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):318-327. [12] Vikas Yadav, Steven Bethard, Mihai Surdeanu. Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering[C]//Proceedings of the Empirical Methods in Natural Language Processing and theInternational Joint Conference on Natural Language Processing, 2019:2578-2589. [13] Samuel R. Bowman, Gabor Angeli, Christopher Potts, et al. A large annotated corpus for learning natural language inference[C]//Proceedings of the Empirical Methods in Natural Language Processing,2015: 632-642. [14] Speer R, Chin J, Havasi C. ConceptNet 5.5: An open multilingual graph of general knowledge[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence, 2017: 4444-4451. [15] Hao Y, Zhang Y, Liu K, et al. An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017:221-231. [16] Denis Lukovnikov, Asja Fischer, Jens Lehmann, et al. Neural network-based question answering over knowledge graphs on word and character level[C]//Proceedings of the 26th International Conference on World Wide Web,2017: 1211-1220. [17] MorGeva, Jonathan Berant. Learning to search in long documents using document structure[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018: 161-176. [18] Mihai Surdeanu, Massimiliano Ciaramita, Hugo Zaragoza. Learning to rank answers on large online QA collections[C]//Proceedings of ACL-08: HLT, 2008: 719-727. [19] Tang M, Cai J, Zhuo H H. Multi-matching network for multiple choice reading comprehension[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:7088-7095. [20] Min S, Zhong V, Socher R, et al. Efficient and robust question answering from minimal context over documents[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics,2018: 1725-1735.
2022, Vol. 36 
