Abstract
Natural language inference plays an essential role in Commonsense Question Answering. Conventional models usually adopt keywords in questions and choices as queries to retrieve static and explicit evidence that is used to obtain final answers, where dynamic interaction between different keywords and implicit relations inference of deeper information are often neglected. In this paper, we propose a novel joint model, the Graph Relation retrieval Reasoning Network (GRRN), to explicitly introduce the dynamic interaction among different keywords and generate informative features that contribute to representation updating. In addition, to pursue in-depth relations between different keywords, we develop an optimised Path Evidence Fusion in the GRRN to obtain evidence based on deep paths and implicit relations with comprehensive knowledge by making full use of the original paths in external knowledge graphs. The experimental results show that compared with the baselines, our approach achieves remarkable improvement of 1.74\(\%\) for precision on the CommonsenseQA dataset, thereby demonstrating the superiority of our state-of-the-art approach on implicit relation inference with deep paths.
Similar content being viewed by others
References
Battaglia PW, Hamrick JB, Bapst V, Sanchez-Gonzalez A, Zambaldi V, Malinowski M, Tacchetti A, Raposo D, Santoro A, Faulkner R, et al. (2018) Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261
Bordes A, Usunier N, Garcia-Durán A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. In: Proceedings of the 26th International Conference on Neural Information Processing Systems, vol 2, pp 2787–2795
Bosselut A, Rashkin H, Sap M, Malaviya C, Celikyilmaz A, Choi Y (2019) Comet: Commonsense transformers for automatic knowledge graph construction. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 4762–4779
Bosselut A, Le Bras R, Choi Y (2021) Dynamic neuro-symbolic knowledge graph construction for zero-shot commonsense question answering. Proceedings of the AAAI Conference on Artificial Intelligence 35:4923–4931
Chen D, Fisch A, Weston J, Bordes A (2017) Reading wikipedia to answer open-domain questions. In: Proceedings of the 55th annual meeting of the association for computational linguistics, vol 1, pp 1870–1879
Chen Q, Ji F, Chen H, Zhang Y (2020) Improving commonsense question answering by graph-based iterative retrieval over multiple knowledge sources. arXiv preprint arXiv:2011.02705
Cho K, van Merrienboer B, Gülçehre Ç, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1724–1734
Clark K, Luong MT, Le QV, Manning CD (2020) Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555
Cui W, Xiao Y, Wang H, Song Y, Hwang Sw, Wang W (2019) Kbqa: learning question answering over qa corpora and knowledge bases. arXiv preprint arXiv:1903.02419
Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805
Doxolodeo K, Mahendra R (2020) Ui at semeval-2020 task 4: Commonsense validation and explanation by exploiting contradiction. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp 614–619
Fadel A, Al-Ayyoub M, Cambria E (2020) Justers at semeval-2020 task 4: Evaluating transformer models against commonsense validation and explanation. In: Proceedings of the fourteenth workshop on semantic evaluation, pp 535–542
Feng Y, Chen X, Lin BY, Wang P, Yan J, Ren X (2020) Scalable multi-hop relational reasoning for knowledge-aware question answering. arXiv preprint arXiv:2005.00646
Gretz S, Bilu Y, Cohen-Karlik E, Slonim N (2020) The workweek is the best time to start a family–a study of gpt-2 based claim generation. arXiv preprint arXiv:2010.06185
Huang Y, Fang M, Zhan X, Cao Q, Liang X, Lin L (2021) Rem-net: Recursive erasure memory network for commonsense evidence refinement. Proceedings of the AAAI Conference on Artificial Intelligence 35:6375–6383
He X, Liu Q, Yang Y (2020) Mv-gnn: multi-view graph neural network for compression artifacts reduction. IEEE Trans Image Process 29:6829–6840
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang X, Zhang J, Li D, Li P (2019) Knowledge graph embedding based question answering. In: Proceedings of the twelfth ACM international conference on web search and data mining, pp 105–113
Ji S, Pan S, Cambria E, Marttinen P, Yu PS (2022) A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans Neural Networks Learn Syst 33(2):494–514
Joshi M, Chen D, Liu Y, Weld DS, Zettlemoyer L, Levy O (2020) Spanbert: improving pre-training by representing and predicting spans. Trans Assoc Comput Linguist 8:64–77
Khashabi D, Khot T, Sabharwal A, Tafjord O, Clark P, Hajishirzi H (2020) Unifiedqa: Crossing format boundaries with a single qa system. arXiv preprint arXiv:2005.00700
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907
Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942
Li L, Gan Z, Cheng Y, Liu J (2019a) Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE/cvf international conference on computer vision, pp 10313–10322
Li S, Chen J, Yu D (2019b) Teaching pretrained models with commonsense reasoning: a preliminary kb-based approach. arXiv preprint arXiv:1909.09743
Lin BY, Chen X, Chen J, Ren X (2019) 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 2822–2832
Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692
Liu Y, Wan Y, He L, Peng H, Yu PS (2021) Kg-bart: knowledge graph augmented bart for generative commonsense reasoning. Proceedings of the AAAI Conference on Artificial Intelligence 35:6418–6425
Loshchilov I, Hutter F (2017) Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101
Lukovnikov D, Fischer A, Lehmann J, Auer S (2017) Neural network-based question answering over knowledge graphs on word and character level. In: Proceedings of the 26th international conference on World Wide Web, pp 1211–1220
Lv S, Guo D, Xu J, Tang D, Duan N, Gong M, Shou L, Jiang D, Cao G, Hu S (2020) Graph-based reasoning over heterogeneous external knowledge for commonsense question answering. Proceedings of the AAAI Conference on Artificial Intelligence 34:8449–8456
Ma K, Francis J, Lu Q, Nyberg E, Oltramari A (2019) Towards generalizable neuro-symbolic systems for commonsense question answering. arXiv preprint arXiv:1910.14087
Ma K, Ilievski F, Francis J, Bisk Y, Nyberg E, Oltramari A (2021) Knowledge-driven data construction for zero-shot evaluation in commonsense question answering. Proceedings of the AAAI Conference on Artificial Intelligence 35:13507–13515
Mihaylov T, Clark P, Khot T, Sabharwal A (2018) 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
Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781
Mishra BD, Tandon N, Clark P (2017) Domain-targeted, high precision knowledge extraction. Trans Assoc Comput Linguist 5:233–246
Mitra A, Banerjee P, Pal KK, Mishra S, Baral C (2019) How additional knowledge can improve natural language commonsense question answering? arXiv preprint arXiv:1909.08855
Na SH, Lee JH (2020) Jbnu at semeval-2020 task 4: Bert and unilm for commonsense validation and explanation. In: Proceedings of the fourteenth workshop on semantic evaluation, pp 527–534
Nickel M, Murphy K, Tresp V, Gabrilovich E (2015) A review of relational machine learning for knowledge graphs. Proc IEEE 104(1):11–33
Nickel M, Rosasco L, Poggio T (2016) Holographic embeddings of knowledge graphs. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp 1955–1961
Peters M, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol 1, pp 2227–2237
Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2019) Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683
Romero J, Razniewski S, Pal K, Z Pan J, Sakhadeo A, Weikum G (2019) Commonsense properties from query logs and question answering forums. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp 1411–1420
Saeedi S, Panahi A, Saeedi S, Fong AC (2020) Cs-nlp team at semeval-2020 task 4: evaluation of state-of-the-art nlp deep learning architectures on commonsense reasoning task. arXiv preprint arXiv:2006.01205
Saha A, Pahuja V, Khapra MM, Sankaranarayanan K, Chandar S (2018) Complex sequential question answering: towards learning to converse over linked question answer pairs with a knowledge graph. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, pp 705–713
Santoro A, Raposo D, Barrett DG, Malinowski M, Pascanu R, Battaglia P, Lillicrap T (2017) A simple neural network module for relational reasoning. In: Advances in neural information processing systems, pp 4967–4976
Sap M, Le Bras R, Allaway E, Bhagavatula C, Lourie N, Rashkin H, Roof B, Smith NA, Choi Y (2019) Atomic: An atlas of machine commonsense for if-then reasoning. Proceedings of the AAAI Conference on Artificial Intelligence 33:3027–3035
Speer R, Chin J, Havasi C (2017) Conceptnet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp 4444–4451
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European semantic web conference, Springer, pp 593–607
Speer R, Chin J, Havasi C (2017) Conceptnet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the AAAI conference on artificial intelligence, vol 31
Strathearn C, Gkatzia D (2021) Chefbot: A novel framework for the generation of commonsense-enhanced responses for task-based dialogue systems. In: Proceedings of the 14th International Conference on Natural Language Generation, pp 46–47
Sun H, Dhingra B, Zaheer M, Mazaitis K, Salakhutdinov R, Cohen W (2018) Open domain question answering using early fusion of knowledge bases and text. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 4231–4242
Talmor A, Herzig J, Lourie N, Berant J (2019) Commonsenseqa: A question answering challenge targeting commonsense knowledge. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1, pp 4149–4158
Tandon N, De Melo G, Weikum G (2017) Webchild 2.0: fine-grained commonsense knowledge distillation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstration, pp 115–120
Wan G, Pan S, Gong C, Zhou C, Haffari G (2021) Reasoning like human: Hierar-chical reinforcement learning for knowledge graph reasoning. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp 1926–1932
Wang C, Liang S, Jin Y, Wang Y, Zhu X, Zhang Y (2020a) Semeval-2020 task 4: commonsense validation and explanation. arXiv preprint arXiv:2007.00236
Wang G, Hou X, Yang D, McKeown K, Huang J (2021) Semantic categorization of social knowledge for commonsense question answering. arXiv preprint arXiv:2109.05168
Wang H, Tang X, Lai S, Leung KS, Zhu J, Fung GPC, Wong KF (2020b) Cuhk at semeval-2020 task 4: Commonsense explanation, reasoning and prediction with multi-task learning. arXiv preprint arXiv:2006.09161
Wang P, Peng N, Szekely P, Ren X (2020c) Connecting the dots: a knowledgeable path generator for commonsense question answering. arXiv preprint arXiv:2005.00691
Wang X, Kapanipathi P, Musa R, Yu M, Talamadupula K, Abdelaziz I, Chang M, Fokoue A, Makni B, Mattei N et al (2019) Improving natural language inference using external knowledge in the science questions domain. Proceedings of the AAAI Conference on Artificial Intelligence 33:7208–7215
Wu S, Li Y, Zhang D, Zhou Y, Wu Z (2020) Topicka: generating commonsense knowledge-aware dialogue responses towards the recommended topic fact. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp 3766–3772
Yan J, Raman M, Zhang T, Rossi R, Zhao H, Kim S, Lipka N, Ren X (2020) Learning contextualized knowledge structures for commonsense reasoning. arXiv preprint arXiv:2010.12873
Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov RR, Le QV (2019) Xlnet: generalized autoregressive pretraining for language understanding. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp 5753–5763
Yasunaga M, Ren H, Bosselut A, Liang P, Leskovec J (2021) Qa-gnn: Reasoning with language models and knowledge graphs for question answering. arXiv preprint arXiv:2104.06378
Ye ZX, Chen Q, Wang W, Ling ZH (2019) Align, mask and select: a simple method for incorporating commonsense knowledge into language representation models. arXiv preprint arXiv:1908.06725
Young T, Cambria E, Chaturvedi I, Zhou H, Biswas S, Huang M (2018) Augmenting end-to-end dialogue systems with commonsense knowledge. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, pp 4970–4977
Zhan X, Huang Y, Dong X, Cao Q, Liang X (2022) Pathreasoner: Explainable reasoning paths for commonsense question answering. Knowl Based Syst 235:107612
Zhang Y, Dai H, Kozareva Z, Smola A, Song L (2018) Variational reasoning for question answering with knowledge graph. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, pp 6069–6076
Zhu C, Cheng Y, Gan Z, Sun S, Goldstein T, Liu J (2019) Freelb: Enhanced adversarial training for natural language understanding. arXiv preprint arXiv:1909.11764
Zhan X, Huang Y, Dong X, Cao Q, Liang X (2022) Pathreasoner: Explainable reasoning paths for commonsense question answering. Knowl Based Syst 235:107612
Huang Y, Fang M, Zhan X, Cao Q, Liang X, Lin L (2021) Rem-net: Recursive erasure memory network for commonsense evidence refinement. Proceedings of the AAAI Conference on Artificial Intelligence 35:6375–6383
Acknowledgements
This work was supported in part by the Consulting Project of Chinese Academy of Engineering under Grant 2020-XY-5, 2018-XY-07, and in part by the Fundamental Research Funds for the Central Universities and the Academy-Locality Cooperation Project of Chinese Academy of Engineering under Grant JS2021ZT05.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, P., Liu, Z., Li, B. et al. Implicit Relation Inference with Deep Path Extraction for Commonsense Question Answering. Neural Process Lett 54, 4751–4768 (2022). https://doi.org/10.1007/s11063-022-10831-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10831-8