1School of Computer Science and Technology, Soochow University, Suzhou 215008, China 2School of Computer Science and Engineering, Changshu Institute of Technology, Changshu 215500, China
[Objective] This paper designs a retrieval model to explore the interpretability of question-answering tasks. It examines the reasoning processes of these reading comprehension models and improves sentence relevance in traditional unsupervised retrieval algorithms. [Methods] We proposed a new unsupervised retrieval model ISR, which integrated modules of Pearson correlation coefficient, GloVe word embeddings, and IDF weighting. The ISR model conducted fine-grained retrieval of inference sentences through multi-round iterations. [Results] The proposed model’s P, R, and F1 metrics were 2.4%, 1.8%, and 2.1% higher than the MSSwQ model on the MultiRC dataset. Its P, R, and F1 metrics were 4.8%, 2.6%, and 3.7% higher than the MSSwQ on the HotPotQA dataset. [Limitations] There might be excessive matching issues due to the model’s retrieval matching mechanism. [Conclusions] The proposed model improves the accuracy of retrieval inference sentences, which can be effectively applied to the question-answering tasks.
(Huang Xingyu. Design and Implementation of Medical Question Answering System Based on ALBERT[D]. Chengdu: University of Electronic Science and Technology of China, 2022.)
[2]
范亦涵. 面向税务的智能问答系统的设计与实现[D]. 济南: 山东大学, 2019.
[2]
(Fan Yihan. The Design and Implementation of Intelligent Question Answering System for Taxation[D]. Jinan: Shandong University, 2019.)
(Huang Weiyi. Deep Neural Networks for Legal Question Answering Based on Knowledge Graph[D]. Shenzhen: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 2020.)
(Hu Yue, Zhou Guangyou. Question Generation from Knowledge Base with Graph Transformer[J]. Journal of Chinese Information Processing, 2022, 36(2): 111-120.)
(Gu Yingjie, Gui Xiaolin, Li Defu, et al. Survey of Machine Reading Comprehension Based on Neural Network[J]. Journal of Software, 2020, 31(7): 2095-2126.)
(Wang Baocheng, Liu Lijun, Huang Qingsong. Retrieval of Similar Questions from Chinese Medical Question Answering Website[J]. Journal of Chinese Information Processing, 2022, 36(6): 135-145.)
(Zhao Yun, Liu Dexi, Wan Changxuan, et al. Retrieval-Based Automatic Question Answer: A Literature Survey[J]. Chinese Journal of Computers, 2021, 44(6): 1214-1232.)
(Yang Shanshan, Jiang Lifen, Sun Huazhi, et al. Multiple Choice Machine Reading Comprehension Based on Temporal Convolutional Network[J]. Computer Engineering, 2020, 46(11): 97-103.)
doi: 10.19678/j.issn.1000-3428.0055628
[9]
Yang Z L, Qi P, Zhang S Z, et al. HotpotQA: A Dataset for Diverse, Explainable Multi-Hop Question Answering[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2018: 2369-2380.
[10]
Reddy S, Chen D Q, Manning C D. CoQA: A Conversational Question Answering Challenge[C]// Proceedings of the Transactions of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2019: 249-266.
[11]
Inoue N, Stenetorp P, Inui K. R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 6740-6750.
[12]
Ho X, Nguyen A K D, Sugawara S, et al. Constructing a Multi-Hop QA Dataset for Comprehensive Evaluation of Reasoning Steps[C]// Proceedings of the 28th International Conference on Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 6609-6625.
[13]
Saxena A, Tripathi A, Talukdar P. Improving Multi-Hop Question Answering over Knowledge Graphs Using Knowledge Base Embeddings[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 4498-4507.
[14]
Lin B Y, Chen X Y, Chen J, et al. KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2019: 2829-2839.
[15]
Yasunaga M, Ren H, Bosselut A, et al. QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering[C]// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2021: 535-546.
[16]
Das R, Dhuliawala S, Zaheer M, et al. Go for a Walk and Arrive at the Answer: Reasoning over Paths in Knowledge Bases Using Reinforcement Learning[C]// Proceedings of the 6th International Conference on Learning Representations. Washington: ICLR, 2018.
[17]
Feng Y L, Chen X Y, Lin B Y, et al. Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2020: 1295-1309.
[18]
Wang P F, Peng N Y, Ilievski F, et al. Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering[C]// Findings of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 4129-4140.
[19]
Yadav V, Bethard S, Surdeanu M. Unsupervised Alignment-Based Iterative Evidence Retrieval for Multi-Hop Question Answering[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 4514-4525.
[20]
Sydorova A, Poerner N, Roth B. Interpretable Question Answering on Knowledge Bases and Text[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2019: 4943-4951.
[21]
Chen D Q, Fisch A, Weston J, et al. Reading Wikipedia to Answer Open-Domain Questions[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2017: 1870-1879.
[22]
Pan L M, Chen W H, Xiong W H, et al. Unsupervised Multi-Hop Question Answering by Question Generation[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2021: 5866-5880.
[23]
Pennington J, Socher R, Manning C D. GloVe: Global Vectors for Word Representation[C]// Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2014: 1532-1543.
(Yang Quan, Sun Yuquan. Research on Semantic Similarity Calculation Based on Depth of CiLin[J]. Computer Engineering and Applications, 2020, 56(17): 48-54.)
doi: 10.3778/j.issn.1002-8331.2001-0249
(Zhang Yangsen, Wang Sheng, Wei Wenjie, et al. An Answer Selection Model Based on Multi-Stage Attention Mechanism with Combination of Semantic Information and Key Information of the Question[J]. Chinese Journal of Computers, 2021, 44(3): 491-507.)
[26]
Vikas Y, Steven B, Mihai S. Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-Hop Question Answering[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2019: 2578-2589.
[27]
Cui Y M, Liu T, Che W X, et al. ExpMRC: Explainability Evaluation for Machine Reading Comprehension[J]. Heliyon, 2022, 8(4): e09290.
doi: 10.1016/j.heliyon.2022.e09290
[28]
Wang A, Singh A, Michael J, et al. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding[C]// Proceedings of the EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Stroudsburg: Association for Computational Linguistics, 2018: 353-355.
[29]
Trivedi H, Kwon H, Khot T, et al. Repurposing Entailment for Multi-Hop Question Answering Tasks[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 2948-2958.
[30]
Sun K, Yu D, Yu D, et al. Improving Machine Reading Comprehension with General Reading Strategies[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 2633-2643.
[31]
Devlin J, Chang M W, Lee K, et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 4171-4186.
[32]
Liu Y H, Ott M, Goyal N, et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach[OL]. arXiv Preprint, arXiv:1907.11692.
[33]
Yang Z L, Dai Z H, Yang Y M, et al. XLNet: Generalized Autoregressive Pretraining for Language Understanding[C]// Proceedings of the 32nd Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2019: 5753-5763.
