Abstract
Answering complex natural language questions requires comprehensive reasoning about the question context and related knowledge. There are two main problems with the existing LM (language model) +KG (knowledge graph) methods. Firstly, they ignore the impact of negative words on Q &A inference. Secondly, they do not consider the effects of contextual entities on relation weight. Taking into account the above issues, we propose a method for Feature Enhanced Structured Reasoning (FESR) that exploits a two-branch graph neural network to improve the structured reasoning ability of question answering. Specifically, FESR first sets feature constraints and changes the attention scores between nodes, thereby strengthening the processing of negative-type question answering, and then optimizes the relation weights to enhance the effect of relations on question-answering inference by introducing contextual entities. We evaluate our model on three datasets in the fields of commonsense reasoning and medical question answering, and the experimental results indicate the effectiveness of our method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bao, J., Duan, N., Yan, Z., Zhou, M., Zhao, T.: Constraint-based question answering with knowledge graph. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2503–2514 (2016)
Chen, J., Hou, H., Gao, J., Ji, Y., Bai, T.: RGCN: recurrent graph convolutional networks for target-dependent sentiment analysis. In: Douligeris, C., Karagiannis, D., Apostolou, D. (eds.) KSEM 2019. LNCS (LNAI), vol. 11775, pp. 667–675. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29551-6_59
Clark, P., et al.: From ‘f’ to ‘a’ on the NY regents science exams: an overview of the aristo project. AI Mag. 41(4), 39–53 (2020)
Feng, Y., Chen, X., Lin, B.Y., Wang, P., Yan, J., Ren, X.: Scalable multi-hop relational reasoning for knowledge-aware question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1295–1309 (2020)
Ishiwatari, T., Yasuda, Y., Miyazaki, T., Goto, J.: Relation-aware graph attention networks with relational position encodings for emotion recognition in conversations, pp. 7360–7370 (2020)
Jin, D., Pan, E., Oufattole, N., Weng, W.H., Fang, H., Szolovits, P.: What disease does this patient have? A large-scale open domain question answering dataset from medical exams. Appl. Sci. 11(14), 6421 (2021)
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Khashabi, D., et al.: UnifiedQA: crossing format boundaries with a single QA system. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1896–1907 (2020)
Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234–1240 (2020)
Lin, B.Y., Chen, X., Chen, J., Ren, X.: KagNet: knowledge-aware graph networks for commonsense reasoning. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2829–2839 (2019)
Liu, F., Shareghi, E., Meng, Z., Basaldella, M., Collier, N.: Self-alignment pretraining for biomedical entity representations. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4228–4238 (2021)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Can a suit of armor conduct electricity? A new dataset for open book question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2381–2391 (2018)
Mihaylov, T., Frank, A.: Knowledgeable reader: enhancing cloze-style reading comprehension with external commonsense knowledge. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 821–832 (2018)
Petroni, F., et al.: Language models as knowledge bases? arXiv preprint arXiv:1909.01066 (2019)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485–5551 (2020)
Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Speer, R., Chin, J., Havasi, C.C.: 5.5: an open multilingual graph of general knowledge. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 4444–4451, December 2016
Sun, H., Dhingra, B., Zaheer, M., Mazaitis, K., Salakhutdinov, R., Cohen, W.W.: Open domain question answering using early fusion of knowledge bases and text (2018)
Talmor, A., Herzig, J., Lourie, N., Berant, J.: CommonsenseQA: a question answering challenge targeting commonsense knowledge. In: Proceedings of NAACL-HLT, pp. 4149–4158 (2019)
Wang, X., et al.: Improving natural language inference using external knowledge in the science questions domain. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7208–7215 (2019)
Yan, J., et al.: Learning contextualized knowledge structures for commonsense reasoning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 4038–4051 (2021)
Yasunaga, M., Ren, H., Bosselut, A., Liang, P., Leskovec, J.: QA-GNN: reasoning with language models and knowledge graphs for question answering. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 535–546 (2021)
Zhang, X., et al.: GreaseLM: graph reasoning enhanced language models. In: International Conference on Learning Representations (2022)
Acknowledgements
This work is supported by grant from the National Natural Science Foundation of China (No. 62076048), the Science and Technology Innovation Foundation of Dalian (2020JJ26GX035).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, L., Chen, H., Qin, X. (2023). Feature Enhanced Structured Reasoning for Question Answering. In: Wang, H., Han, X., Liu, M., Cheng, G., Liu, Y., Zhang, N. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph Empowers Artificial General Intelligence. CCKS 2023. Communications in Computer and Information Science, vol 1923. Springer, Singapore. https://doi.org/10.1007/978-981-99-7224-1_15
Download citation
DOI: https://doi.org/10.1007/978-981-99-7224-1_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7223-4
Online ISBN: 978-981-99-7224-1
eBook Packages: Computer ScienceComputer Science (R0)