Review of Conversational Machine Reading Comprehension

doi:10.3778/j.issn.1673-9418.2102039

Abstract

Abstract:

Machine reading comprehension (MRC) is a research field driven by datasets. The task of MRC is to make the machine correctly answer relevant questions on the basis of understanding the natural language text. But limited by datasets, most of the machine reading comprehension tasks are single-turn question answering, and there is no dependency between question answering pairs. Conversational question answering (ConvQA) is the human-computer process that enables the machine to carry out continuous topics when it helps human to obtain information. In recent years, with the development of MRC datasets and deep neural networks, researchers combine machine reading com-prehension and conversational question answering to form a new more complex field, conversational machine com-prehension (CMC). This has greatly boosted the field of MRC. This paper summarizes the latest research progress of CMC in recent years from three aspects. Firstly, it describes the definition of CMC task, the challenges and the characteristics of the datasets. Then, it summarizes the research progress and the current architecture of the latest models, and focuses on the relevant technical methods used in conversational history embedding and conversational reasoning. Finally, this paper analyzes the current model of CMC, and prospects the future research hotspots and methods of CMC.

Key words: multi-turn conversation, machine reading comprehension (MRC), conversational question answering (ConvQA)

摘要：

机器阅读理解（MRC）是一个受数据集推动的研究领域，其目标是让机器在理解文章内容的基础上能够正确回答相关问题。早期受数据集限制，机器阅读理解任务大多局限于单轮问答，问答对之间缺少依赖关系。而会话问答（ConvQA）是使机器在帮助人类获取信息时可以进行连续主题的人机交互过程。近年来，随着机器阅读理解数据集和深度神经网络的发展，研究人员将机器阅读理解与会话问答结合，形成更为复杂真实的会话式机器阅读理解（CMC），这极大地推动了机器阅读理解领域的发展。对近几年会话式机器阅读理解相关最新研究进展从三方面归纳总结：首先阐述该任务的定义、所面临的挑战以及相关数据集的特性；然后归纳总结当前最新模型的架构及其研究进展，着重介绍会话历史嵌入表示以及会话推理所使用的相关技术方法；最后梳理分析当前会话式机器阅读理解模型，并对未来研究重点和研究方法进行展望。

关键词: 多轮对话, 机器阅读理解（MRC）, 会话问答（ConvQA）

LI Kun, LI Yanling, LIN Min. Review of Conversational Machine Reading Comprehension[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(9): 1607-1618.

李堃, 李艳玲, 林民. 会话式机器阅读理解综述[J]. 计算机科学与探索, 2021, 15(9): 1607-1618.

References

[1] TURING A M I. Computing machinery and intelligence[J]. Mind, 1950(236): 433-460.
[2] LEHNERT W G. The process of question and answering[M]. New Haven: Yale University, 1977.
[3] SAEIDI M, BARTOLO M, LEWIS P, et al. Interpretation of natural language rules in conversational machine reading[J]. arXiv:1809.01494, 2018.
[4] REDDY S, CHEN D, MANNING C D. CoQA: a conversational question answering challenge[J]. Transactions of the Association for Computational Linguistics, 2019, 7: 249-266.
[5] CHOI E, HE H, IYYER M, et al. QuAC: question answering in context[C]//Proceedings of the 2018 Conference on Emp-irical Methods in Natural Language Processing and the 8th International Joint Conference on Natural Language Pro-cessing, Brussels, Nov 2-4, 2018. Stroudsburg: ACL, 2018: 2174-2184.
[6] SEO M J, KEMBHAVI A, FARHADI A, et al. Bidirectional attention flow for machine comprehension[C]//Proceedings of the 5th International Conference on Learning Representations, Toulon, Apr 24-26, 2017: 25-32.
[7] HERMANN K M, KOCISKY T, GREFENSTETTE E, et al. Teaching machines to read and comprehend[C]//Proceedings of the 28th Annual Conference on Neural Information Proc-essing Systems, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 1693-1701.
[8] IYYER M, YIH W, CHANG M, et al. Search-based neural structured learning for sequential question answering[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Jul 30-Aug 4, 2017. Stroudsburg: ACL, 2017: 1821-1831.
[9] TALMOR A, BERANT J. The Web as a knowledge-base for answering complex questions[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Jun 1-6, 2018. Stroudsburg: ACL, 2018: 641-651.
[10] SAHA A, PAHUJA V, KHAPRA M M, et al. Complex sequential question answering: towards learning to converse over linked question answer pairs with a knowledge graph[C]//Proceed-ings of the 32nd Association for the Advancement of Artificial Intelligence, New Orleans, Feb 2-7, 2018: 705-713.
[11] RICHARDSON M, BURGES C J C, RENSHAW E. MCTest: a challenge dataset for the open-domain machine compre-hension of text[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Oct 18-21, 2013. Stroudsburg: ACL, 2013: 193-203.
[12] LAI G K, XIE Q Z, LIU H X, et al. RACE: large-scale reading comprehension dataset from examinations[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Sep 9-11, 2017. Strouds-burg: ACL, 2017: 785-794.
[13] YATSKAR M. A qualitative comparison of CoQA, SQuAD 2.0 and QuAC[J]. arXiv:1809.10735, 2018.
[14] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[15] PENNINGTON J, SOCHER R, MANNING C D. GloVe: GlobalVectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1532-1543.
[16] KIM Y. Convolutional neural networks for sentence classifi-cation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1746-1751.
[17] LEE K, SALANT S, KWIATKOWSKI T, et al. Learning recurrent span representations for extractive question answering[J]. arXiv:1611.01436, 2016.
[18] WU H C, LUK R W P, WONG K F, et al. Interpreting TF-IDF term weights as making relevance decisions[J]. ACM Trans-actions on Information Systems, 2008, 26(3): 1-37.
[19] SRIVASTAVA R K, GREFF K, SCHMIDHUBER J. Highway networks[J]. arXiv:1505.00387, 2015.
[20] ZHU C G, ZENG M, HUANG X D. SDNet: contextualized attention-based deep network for conversational question answering[J]. arXiv:1812.03593, 2018.
[21] SENNRICH R, HADDOW B, BIRCH A. Neural machine translation of rare words with subword units[C]//Proceedings of the 54th Annual Meeting of the Association for Computa-tional Linguistics, Berlin, Aug 7-12, 2016. Stroudsburg: ACL, 2016: 1715-1725.
[22] QU C, YANG L, QIU M, et al. BERT with history answer embedding for conversational question answering[C]//Pro-ceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, Jul 21-25, 2019. New York: ACM, 2019: 1133-1136.
[23] QU C, YANG L, QIU M, et al. Attentive history selection for conversational question answering[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, Nov 3-7, 2019. New York: ACM, 2019: 1391-1400.
[24] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv: 1409.0473, 2014.
[25] CUI Y, CHEN Z, WEI S, et al. Attention-over-attention neural networks for reading comprehension[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Jul 30-Aug 4, 2017. Stroudsburg: ACL, 2017: 593-602.
[26] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. arXiv:1706.03762, 2017.
[27] HOCHREITER S, SCHMIDHUBER J. Long short-term mem-ory[J]. Neural Computation, 1997, 9(8): 1735-780.
[28] HUANG H, ZHU C, SHEN Y, et al. FusionNet: fusing via fully-aware attention with application to machine compre-hension[C]//Proceedings of the 6th International Conference on Learning Representations, Vancouver, Apr 30-May 3, 2018: 66-76.
[29] HUANG H Y, CHOI E, YIH W T. FlowQA: grasping flow in history for conversational machine comprehension[C]//Proceedings of the 7th International Conference on Learning Representations, New Orleans, May 6-9, 2019: 1354-1364.
[30] CHEN Y, WU L F, ZAKI M J. Graphflow: exploiting con-versation flow with graph neural networks for conversational machine comprehension[C]//Proceedings of the 29th Inter-national Joint Conference on Artificial Intelligence, Yokohama, Jul 2020: 1452-1462.
[31] CHO K, VAN MERRIENBOER B, 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 Pro-cessing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1724-1734.
[32] LI Y, TARLOW D, BROCKSCHMIDT M, et al. Gated graph sequence neural networks[J]. arXiv:1511.05493, 2015.
[33] CHEN D, 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 Lin-guistics, Vancouver, Jul 30-Aug 4, 2017. Stroudsburg: ACL, 2017: 1870-1879.
[34] SEE A, LIU P J, MANNING C D. Get to the point: summa-rization with pointer-generator networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Jul 30-Aug 4, 2017. Stroudsburg: ACL, 2017: 1073-1083.
[35] YEH Y T, CHEN Y N. Flowdelta: modeling flow information gain in reasoning for conversational machine comprehen-sion[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th Interna-tional Joint Conference on Natural Language Processing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 86-90.
[36] ZHANG X. MC2: multi-perspective convolutional cube for conversational machine reading comprehension[C]//Procee-dings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Jul 28-Aug 2, 2019. Stroudsburg: ACL, 2019: 6185-6190.
[37] OHSUGI Y, SAITO I, NISHIDA K, et al. A simple but effective method to incorporate multi-turn context with BERT for conversational machine comprehension[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Jul 28-Aug 2, 2019. Stroudsburg: ACL, 2019: 11-17.
[38] GONG H, SHEN Y, YU D, et al. Recurrent chunking mech-anisms for long-text machine reading comprehension[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Jul 5-10, 2020. Stroudsburg: ACL, 2020: 6751-6761.