{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:37:15Z","timestamp":1740184635148,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Natural language inference (NLI) is a fundamental task of natural language processing (NLP). Most recent NLI research has focused on explaining the model\u2019s decisions in generating causal explanations (i.e., why did a premise\/hypothesis pair as input lead to their inference relation as output?). As layer-based language models can learn language structure information, this paper conducts a sample-by-sample analysis of the linguistic feature relation between premise and hypothesis that is expected to guide NLI modeling and interpretation better. Our empirical study verifies that the linguistic feature relation of premise\/hypothesis pairs can be seen in NLI inference models, which can be used to interpret inference samples. Meanwhile, experimental results show that these linguistic features relation interpretation can help the NLI model achieve comparable inference accuracy compared with state-of-the-art methods.<\/jats:p>","DOI":"10.1007\/s44230-023-00054-y","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T10:02:25Z","timestamp":1711101745000},"page":"127-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Linguistic Feature Relation Analysis of Premise and Hypothesis for Interpreting Nature Language Inference"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2876-3888","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"54_CR1","volume-title":"Natural Language Inference","author":"B MacCartney","year":"2009","unstructured":"MacCartney B. Natural Language Inference. Stanford University; 2009."},{"key":"54_CR2","doi-asserted-by":"crossref","unstructured":"Peters ME, Neumann M, Zettlemoyer L, Yih W. Dissecting contextual word embeddings: Architecture and representation. In: Proceedings of the 2018 Conference on EMNLP. ACL; 2018. p. 1499\u20131509.","DOI":"10.18653\/v1\/D18-1179"},{"key":"54_CR3","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C. Why should I trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM International Conference in August 13\u201317, 2016. ACM; 2016. p. 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"54_CR4","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674736061","volume-title":"The black box society: the secret algorithms that control money and information","author":"F Pasquale","year":"2015","unstructured":"Pasquale F. The black box society: the secret algorithms that control money and information. Harvard University Press; 2015."},{"key":"54_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1424","author":"PP Angelov","year":"2021","unstructured":"Angelov PP, Soares EA, Jiang R, Arnold NI, Atkinson PM. Explainable artificial intelligence: an analytical review. WIREs Data Min Knowl Discov. 2021. https:\/\/doi.org\/10.1002\/widm.1424.","journal-title":"WIREs Data Min Knowl Discov"},{"key":"54_CR6","doi-asserted-by":"crossref","unstructured":"Kumar S, Talukdar PP. NILE: Natural language inference with faithful natural language explanations. In: Proceedings of the 58th Annual Meeting of ACL 2020. ACL; 2020. p. 8730\u20138742.","DOI":"10.18653\/v1\/2020.acl-main.771"},{"key":"54_CR7","doi-asserted-by":"crossref","unstructured":"Chen Q, Ji F, Zeng X, Li F, Zhang J, Chen H, Zhang Y. KACE: generating knowledge aware contrastive explanations for natural language inference. In: Proceedings of the 59th Conference of ACL\/IJCNLP 2021, (Volume 1: Long Papers). ACL; 2021. p. 2516\u20132527.","DOI":"10.18653\/v1\/2021.acl-long.196"},{"key":"54_CR8","doi-asserted-by":"crossref","unstructured":"Kalouli A, Sevastjanova R, Paiva V, Crouch RS, El-Assady M. Xplainli: Explainable natural language inference through visual analytics. In: Proceedings of the 28th Conference of COLING 2020: System Demonstrations. ICCL; 2020. p. 48\u201352.","DOI":"10.18653\/v1\/2020.coling-demos.9"},{"key":"54_CR9","doi-asserted-by":"crossref","unstructured":"Gilpin LH, Bau D, Yuan BZ, Bajwa A, Specter MA, Kagal L. Explaining explanations: An overview of interpretability of machine learning. In: 5th Conference of IEEE, DSAA 2018. IEEE; 2018. p. 80\u201389.","DOI":"10.1109\/DSAA.2018.00018"},{"key":"54_CR10","doi-asserted-by":"crossref","unstructured":"Jawahar G, Sagot B, Seddah D. What does BERT learn about the structure of language? In: Proceedings of the 57th Conference ACL 2019, Volume 1: Long Papers. ACL; 2019. p. 3651\u20133657.","DOI":"10.18653\/v1\/P19-1356"},{"key":"54_CR11","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. 2017; p. 5998\u20136008."},{"key":"54_CR12","unstructured":"Socher R, Manning CD. Deep learning for NLP (without magic). In: Human Language Technologies: Conference of the North American Chapter of the ACL, Proceedings. ACL; 2013. p. 1\u20133."},{"issue":"11","key":"54_CR13","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G. Visualizing data using t-sne. J Mach Learn Res. 2008;9(11):2579\u2013605.","journal-title":"J Mach Learn Res"},{"key":"54_CR14","unstructured":"Adi Y, Kermany E, Belinkov Y, Lavi O, Goldberg Y. Fine-grained analysis of sentence embeddings using auxiliary prediction tasks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net 2017."},{"issue":"2","key":"54_CR15","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1109\/TVCG.2020.3030342","volume":"27","author":"F Cheng","year":"2021","unstructured":"Cheng F, Ming Y, Qu H. DECE: decision explorer with counterfactual explanations for machine learning models. IEEE Trans Vis Comput Graph. 2021;27(2):1438\u201347.","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"54_CR16","doi-asserted-by":"crossref","unstructured":"Park DH, Hendricks LA, Akata Z, Rohrbach A, Schiele B, Darrell T, Rohrbach M. Multimodal explanations: Justifying decisions and pointing to the evidence. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society; 2018. p. 8779\u20138788.","DOI":"10.1109\/CVPR.2018.00915"},{"key":"54_CR17","doi-asserted-by":"crossref","unstructured":"Vig J. A multiscale visualization of attention in the transformer model. In: Costa-juss\u00e0 MR, Alfonseca E (eds.) Proceedings of the 57th Conference of ACL 2019, Volume 3: System Demonstrations. ACL; 2019. p. 37\u201342.","DOI":"10.18653\/v1\/P19-3007"},{"key":"54_CR18","doi-asserted-by":"crossref","unstructured":"Kim S, Kang I, Kwak N. Semantic sentence matching with densely-connected recurrent and co-attentive information. In: The Thirty-Third AAAI Conference on Artificial Intelligence. AAAI Press; 2019. p. 6586\u20136593.","DOI":"10.1609\/aaai.v33i01.33016586"},{"key":"54_CR19","doi-asserted-by":"crossref","unstructured":"Gururangan S, Swayamdipta S, Levy O, Schwartz R, Bowman SR, Smith NA. Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of NAACL-HLT, New Orleans, 2018. ACL; 2018. p. 107\u2013112.","DOI":"10.18653\/v1\/N18-2017"},{"key":"54_CR20","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V. Roberta: a robustly optimized BERT pretraining approach, 2019. CoRR arXiv:1907.11692."},{"key":"54_CR21","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR, 2015."},{"key":"54_CR22","unstructured":"Devlin J, Chang M, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of NAACL-HLT 2019, Volume 1 (Long and Short Papers). ACL; 2019. p. 4171\u20134186."},{"key":"54_CR23","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell JG, Salakhutdinov R, Le QV. Xlnet: Generalized autoregressive pretraining for language understanding. In: Advances in NeurIPS 32: Annual Conference on NeurIPS 2019. 2019; p. 5754\u20135764"},{"key":"54_CR24","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I, et al. Improving language understanding by generative pre-training, 2018."},{"key":"54_CR25","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. In: 3rd ICLR 2015, Conference Track Proceedings, 2015."},{"key":"54_CR26","doi-asserted-by":"crossref","unstructured":"Ghaeini R, Hasan SA, Datla VV, Liu J, Lee K, Qadir A, Ling Y, Prakash A, Fern XZ, Farri O. Dr-bilstm: Dependent reading bidirectional LSTM for natural language inference. In: Proceedings of the 2018 Conference of NAACL-HLT 2018, Volume 1 (Long Papers). ACL; 2018. p. 1460\u20131469.","DOI":"10.18653\/v1\/N18-1132"},{"key":"54_CR27","doi-asserted-by":"crossref","unstructured":"Pan B, Yang Y, Zhao Z, Zhuang Y, Cai D, He X. Discourse marker augmented network with reinforcement learning for natural language inference. In: Proceedings of the 56th Annual Meeting of ACL 2018, Volume 1: Long Papers. ACL; 2018. p. 989\u2013999.","DOI":"10.18653\/v1\/P18-1091"},{"key":"54_CR28","doi-asserted-by":"crossref","unstructured":"Zhang Z, Wu Y, Zhao H, Li Z, Zhang S, Zhou X, Zhou X. Semantics-aware BERT for language understanding. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence. AAAI Press; 2020. p. 9628\u20139635.","DOI":"10.1609\/aaai.v34i05.6510"},{"key":"54_CR29","unstructured":"Pilault J, Elhattami A, Pal CJ. Conditionally adaptive multi-task learning: Improving transfer learning in NLP using fewer parameters & less data. In: 9th ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net, 2021."}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-023-00054-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-023-00054-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-023-00054-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T10:26:26Z","timestamp":1713349586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-023-00054-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["54"],"URL":"https:\/\/doi.org\/10.1007\/s44230-023-00054-y","relation":{},"ISSN":["2667-1336"],"issn-type":[{"type":"electronic","value":"2667-1336"}],"subject":[],"published":{"date-parts":[[2024,3,22]]},"assertion":[{"value":"28 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests. Author Lin Li is a member of the Editorial Board of Journal Human-Centric Intelligent Systems. The paper was handled by another Editor and has undergone a rigorous peer review process. Author Lin Li was not involved in the journal\u2019s peer review of, or decisions related to, this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}