Abstract
Generally, the candidate options for multiple choice machine reading comprehension (MRC) are not explicitly present in the document and need to be inferred from text or even from the world’s knowledge. Previous work endeavored to improve performance with the aid of commonsense knowledge or using multi-step reasoning strategy. However, there is no model adopt multi-step reasoning with external commonsense knowledge information to solve multiple choice MRC, and two shortcomings still remain unsolved, i.e., external knowledge may involve undesirable noise and only the latest reasoning step makes contribution to the next reasoning. To address the above issues, we propose a multi-step reasoning neural network based on the strong Co-Matching model with the aid of commonsense knowledge. Firstly, we present a sentence-level knowledge interaction (SKI) module to integrate commonsense knowledge with corresponding sentence rather than the whole MRC instance. Secondly, we present a residual connection-based multi-step reasoning (RCMR) answer module, which makes the next reasoning depending on the integration of several early reasoning steps rather than only the latest reasoning step. The comparative experimental results on MCScript show that our single model achieves a promising result comparable to SOTA single model with extra samples and specifically achieves the best result for commonsense type questions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
We use the code on https://github.com/shuohangwang/comatch to implement Co-Matching model. But one difference is that we add binary features to the word embedding.
- 10.
The ensemble results of the HMA and the TriAN were 84.13% and 83.95% in SemEval-2018 Task 11, respectively. Table 2 shows the results of their single models.
- 11.
The “commonsense” type questions accuracy of MITRE is reported in reference [27].
- 12.
We use the code on https://github.com/intfloat/commonsense-rc to implement TriAN model.
References
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: EMNLP, pp. 2383–2392 (2016)
Hermann, K.M., et al.: Teaching machines to read and comprehend. In: NIPS, pp. 1693–1701 (2015)
Ostermann, S., Modi, A., Roth, M., Thater, S., Pinkal, M.: MCScript: a novel dataset for assessing machine comprehension using script knowledge. In: LREC (2018)
Zhu, H., Wei, F., Qin, B., Liu, T.: Hierarchical attention flow for multiple-choice reading comprehension. In: AAAI (2018)
Parikh, S., Sai, A.B., Nema, P., Khapra, M.M.: ElimiNet: a model for eliminating options for reading comprehension with multiple choice questions. In: IJCAI, pp. 4272–4278 (2018)
Wang, S., Yu, M., Jiang, J., Chang, S.: A co-matching model for multi-choice reading comprehension. In: ACL, pp. 746–751 (2018)
Shen, Y., Huang, P.-S., Gao, J., Chen, W.: ReasoNet: learning to stop reading in machine comprehension. In: SIGKDD, pp. 1047–1055 (2017)
Tang, M., Cai, J., Zhuo, H.H.: Multi-matching network for multiple choice reading comprehension. In: AAAI (2019)
Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: AAAI, pp. 4444–4451 (2017)
Wang, L., Sun, M., Zhao, W., Shen, K., Liu, J.: Yuanfudao at SemEval-2018 task 11: three-way attention and relational knowledge for commonsense machine comprehension. In: SemEval, pp. 758–762 (2018)
Chen, W., Quan, X., Chen, C.: Gated convolutional networks for commonsense machine comprehension. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11301, pp. 297–306. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04167-0_27
Mihaylov, T., Frank, A.: Knowledgeable reader: enhancing cloze-style reading comprehension with external commonsense knowledge. In: ACL, pp. 821–832 (2018)
Xu, Y., Liu, J., Gao, J., Shen, Y., Liu, X.: Dynamic fusion networks for machine reading comprehension. arXiv preprint arXiv:1711.04964 (2017)
Liu, X., Shen, Y., Duh, K., Gao, J.: Stochastic answer networks for machine reading comprehension. In: ACL, pp. 1694–1704 (2018)
Dhingra, B., Liu, H., Yang, Z., Cohen, W., Salakhutdinov, R.: Gated-attention readers for text comprehension. In: ACL, pp. 1832–1846 (2017)
Bond, F., Foster, R.: Linking and extending an open multilingual wordNet. In: ACL, pp. 1352–1362 (2013)
Kuo, Y.-L., et al.: Community-based game design: experiments on social games for commonsense data collection. In: Proceedings of the ACM SIGKDD Workshop on Human Computation, pp. 15–22. ACM (2009)
Nakahara, K., Yamada, S.: Development and evaluation of a web-based game for common-sense knowledge acquisition in Japan. Unisys Technol. Rev. 30(4), 295–305 (2011)
Von Ahn, L., Kedia, M., Blum, M.: Verbosity: a game for collecting common-sense facts. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 75–78. ACM (2006)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)
Tang, D., Qin, B., Liu, T.: Document modeling with gated recurrent neural network for sentiment classification. In: EMNLP, pp. 1422–1432 (2015)
Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. In: ACL, pp. 1556–1566 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Chen, Z., Cui, Y., Ma, W., Wang, S., Liu, T., Hu, G.: HFL-RC system at SemEval-2018 task 11: hybrid multi-aspects model for commonsense reading comprehension. arXiv preprint arXiv:1803.05655 (2018)
Merkhofer, E., Henderson, J., Bloom, D., Strickhart, L., Zarrella, G.: MITRE at SemEval-2018 task 11: commonsense reasoning without commonsense knowledge. In: SemEval, pp. 1078–1082 (2018)
Ostermann, S., Roth, M., Modi, A., Thater, S., Pinkal, M.: SemEval-2018 task 11: Machine comprehension using commonsense knowledge. In: SemEval, pp. 747–757 (2018)
Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: Race: large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sheng, Y., Lan, M. (2019). Residual Connection-Based Multi-step Reasoning via Commonsense Knowledge for Multiple Choice Machine Reading Comprehension. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11955. Springer, Cham. https://doi.org/10.1007/978-3-030-36718-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-36718-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36717-6
Online ISBN: 978-3-030-36718-3
eBook Packages: Computer ScienceComputer Science (R0)