Abstract
Logical reasoning plays a very important role in Natural Language Understanding. In recent years, research on logical reasoning has shown a booming trend. Previous works either construct graphs to perform implicit reasoning or augment labeled training data with consistent symbol logical rules. In this paper, we combine the advantages of both graph based implicit reasoning and symbolic logic based consistent transformation in a deep learning framework. In order to make full use of the semantic and logical structures in text, we exploit Abstract Meaning Representation (AMR) to help logical reasoning, which can explicitly provide core semantic knowledge and logical structures. Based on AMR graph extracted, we design two tasks: 1) Construct joint graph and strengthen the interaction between context and option subgraph to predict right choice. 2) Leverage symbolic rules to construct logical consistent and inconsistent graphs to let model identify and differentiate logical structures in different graphs by contrastive learning. Experiments are conducted on two logical reasoning datasets: Reclor and LogiQA. And our method has a significant improvement over the baselines and most previous methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anchiêta, R., Pardo, T.: Semantically inspired AMR alignment for the Portuguese language. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1595–1600 (2020)
Bai, X., Chen, Y., Song, L., Zhang, Y.: Semantic representation for dialogue modeling. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 4430–4445 (2021)
Bai, X., Chen, Y., Zhang, Y.: Graph pre-training for AMR parsing and generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p. todo, May 2022
Banarescu, L., et al.: Abstract meaning representation for sembanking. In: Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pp. 178–186. Association for Computational Linguistics (2013)
Bevilacqua, M., Blloshmi, R., Navigli, R.: One spring to rule them both: symmetric AMR semantic parsing and generation without a complex pipeline. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)
Blodgett, A., Schneider, N.: Probabilistic, structure-aware algorithms for improved variety, accuracy, and coverage of AMR alignments. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, August 2021
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)
Huang, Y., Fang, M., Cao, Y., Wang, L., Liang, X.: DAGN: discourse-aware graph network for logical reasoning. In: NAACL (2021)
Hurley, P.J.: A concise introduction to logic. Cengage Learning (2014)
Jiao, F., Guo, Y., Song, X., Nie, L.: MERIt: meta-path guided contrastive learning for logical reasoning. In: Findings of ACL. ACL (2022)
Kapanipathi, P., et al.: Leveraging abstract meaning representation for knowledge base question answering. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 3884–3894 (2021)
Lam, H.T., et al.: Ensembling graph predictions for AMR parsing. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6–14 December 2021, virtual (2021)
Li, X., Cheng, G., Chen, Z., Sun, Y., Qu, Y.: AdaLoGN: adaptive logic graph network for reasoning-based machine reading comprehension. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 7147–7161 (2022)
Lim, J., Oh, D., Jang, Y., Yang, K., Lim, H.S.: I know what you asked: graph path learning using AMR for commonsense reasoning. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 2459–2471 (2020)
Liu, F., Flanigan, J., Thomson, S., Sadeh, N., Smith, N.A.: Toward abstractive summarization using semantic representations. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1077–1086 (2015)
Liu, J., Cui, L., Liu, H., Huang, D., Wang, Y., Zhang, Y.: LogiQA: a challenge dataset for machine reading comprehension with logical reasoning. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 3622–3628 (2021)
Liu, Y., Che, W., Zheng, B., Qin, B., Liu, T.: An AMR aligner tuned by transition-based parser. In: EMNLP (2018)
Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach (2020)
Ouyang, S., Zhang, Z., Zhao, H.: Fact-driven logical reasoning. arXiv preprint arXiv:2105.10334 (2021)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383–2392 (2016)
Schlichtkrull, M.S., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: ESWC (2018)
Song, L., Gildea, D., Zhang, Y., Wang, Z., Su, J.: Semantic neural machine translation using AMR. Trans. Assoc. Comput. Linguist. 7, 19–31 (2019)
Wang, S., et al.: From LSAT: the progress and challenges of complex reasoning. IEEE/ACM Trans. Audio Speech Lang. Process. (2022)
Wang, S., et al.: Logic-driven context extension and data augmentation for logical reasoning of text (2021)
Xu, W., Zhang, H., Cai, D., Lam, W.: Dynamic semantic graph construction and reasoning for explainable multi-hop science question answering. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 1044–1056 (2021)
Yang, Z., et al.: HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2018)
Yu, W., Jiang, Z., Dong, Y., Feng, J.: ReClor: a reading comprehension dataset requiring logical reasoning. In: International Conference on Learning Representations (ICLR), April 2020
Zhou, J., Naseem, T., Astudillo, R.F., Florian, R.: AMR parsing with action-pointer transformer. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5585–5598 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, X., Zhang, T., Lu, Y., Liu, G. (2022). LoCSGN: Logic-Contrast Semantic Graph Network for Machine Reading Comprehension. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13551. Springer, Cham. https://doi.org/10.1007/978-3-031-17120-8_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-17120-8_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17119-2
Online ISBN: 978-3-031-17120-8
eBook Packages: Computer ScienceComputer Science (R0)
