{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:33:53Z","timestamp":1759883633424,"version":"build-2065373602"},"reference-count":41,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002380","name":"Hanyang University","doi-asserted-by":"publisher","award":["No.RS\u20102020\u2010II201373"],"award-info":[{"award-number":["No.RS\u20102020\u2010II201373"]}],"id":[{"id":"10.13039\/501100002380","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:p>Contrastive learning of sentence representations has achieved great improvements in several natural language processing tasks. However, the supervised contrastive learning model trained on the natural language inference (NLI) dataset is insufficient to elucidate the semantics of sentences since it is prone to make a prediction based on heuristics. Herein, by using the ParsEVAL and the word overlap metric, it is shown that sentence pairs in the NLI dataset have strong syntactic similarity and propose a framework to compensate for this problem in two aspects. 1) Apply simple syntactic transformations to the hypothesis and 2) expand the objective to SupCon Loss to leverage variants of sentences. The method is evaluated on semantic textual similarity (STS) tasks and transfer tasks. The proposed methods improve the performance of the BERT\u2010based baseline in STS Benchmark and SICK Relatedness by 1.48% and 2.2%. Furthermore, the model achieves 82.65% on the HANS benchmark dataset, to the best of our knowledge, which is a state\u2010of\u2010the\u2010art performance demonstrating that our approach is effective in grasping semantics without heuristics in the NLI dataset at supervised contrastive learning. The code is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/whnhch\/Break-the-Similarity\">https:\/\/github.com\/whnhch\/Break-the-Similarity<\/jats:ext-link>.<\/jats:p>","DOI":"10.1002\/aisy.202300717","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T10:44:49Z","timestamp":1721040289000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Simple Data Transformations for Mitigating the Syntactic Similarity to Improve Sentence Embeddings at Supervised Contrastive Learning"],"prefix":"10.1002","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6441-0441","authenticated-orcid":false,"given":"Minji","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Whanhee","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea"},{"name":"School of Computing University of Utah  Utah 84112 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soohyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Suk","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea"},{"name":"Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2024,7,15]]},"reference":[{"key":"e_1_2_11_2_1","unstructured":"J.Devlin M.\u2010W.Chang K.Lee K.Toutanova inProc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long and Short Papers) Association for Computational Linguistics Stroudsburg PA2019 pp.4171\u20134186."},{"key":"e_1_2_11_3_1","unstructured":"Y.Liu M.Ott N.Goyal J.Du M.Joshi D.Chen O.Levy M.Lewis L.Zettlemoyer V.Stoyanov arXiv preprint arXiv:1907.11692 2019."},{"key":"e_1_2_11_4_1","unstructured":"N.Reimers I.Gurevych inProc. of the 2019 Conf. on Empirical Methods in Natural Language Processing Association for Computational Linguistics Stroudsburg PA2019."},{"key":"e_1_2_11_5_1","unstructured":"T.Gao X.Yao D.Chen inProc. of the 2021 Conf. on Empirical Methods in Natural Language Processing Association for Computational Linguistics Stroudsburg PA2021 pp.6894\u20136910."},{"key":"e_1_2_11_6_1","unstructured":"T.Chen S.Kornblith M.Norouzi G.Hinton A Simple Framework for Contrastive Learning of Visual Representations arXiv:2002.05709 2020."},{"key":"e_1_2_11_7_1","unstructured":"S. R.Bowman G.Angeli C.Potts C. D.Manning. inProc. of the 2015 Conf. on Empirical Methods in Natural Language Processing Association for Computational Linguistics Stroudsburg PA2015 pp.632\u2013642."},{"key":"e_1_2_11_8_1","unstructured":"A.Williams N.Nangia S.Bowman inProc. of the 2018 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long Papers) Association for Computational Linguistics Stroudsburg PA2018 pp.1112\u20131122."},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"A.Gupta G.Kvernadze V.Srikumar in Proc. of the AAAI Conf. on Artificial Intelligence Proceedings of the AAAI conference on artificial intelligence. Vol.35 2021 pp.12946\u201312954.","DOI":"10.1609\/aaai.v35i14.17531"},{"key":"e_1_2_11_10_1","unstructured":"T.McCoy E.Pavlick T.Linzen inProc. of the 57th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Stroudsburg PA2019 pp.3428\u20133448."},{"key":"e_1_2_11_11_1","unstructured":"E.Black S.Abney D.Flickenger C.Gdaniec R.Grishman P.Harrison D.Hindle R.Ingria F.Jelinek J.Klavans M.Liberman M.Marcus S.Roukos B.Santorini T.Strzalkowski presented atSpeech and Natural Language: Proc. of a Workshop Pacific Grove California February 1991."},{"key":"e_1_2_11_12_1","unstructured":"J.Wei K.Zou inProc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Inter. Joint Conf. on Natural Language Processing (EMNLP\u2010IJCNLP) Association for Computational Linguistics Stroudsburg PA2019 pp.6382\u20136388."},{"key":"e_1_2_11_13_1","unstructured":"A.Karimi L.Rossi A.Prati inFindings of the Association for Computational Linguistics: EMNLP 2021 Association for Computational Linguistics Stroudsburg PA2021 pp.2748\u20132754."},{"key":"e_1_2_11_14_1","unstructured":"P.Khosla P.Teterwak C.Wang A.Sarna Y.Tian P.Isola A.Maschinot C.Liu D.Krishnan Supervised Contrastive Learning arXiv:2004.11362 2020."},{"key":"e_1_2_11_15_1","unstructured":"K.He H.Fan Y.Wu S.Xie R.Girshick inIEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2020 pp.9726\u20139735."},{"key":"e_1_2_11_16_1","unstructured":"C.Jia Y.Yang Y.Xia Y.\u2010T.Chen Z.Parekh H.Pham Q.Le Y.\u2010H.Sung Z.Li T.Duerig inProc. of the 38th Inter. Conf. on Machine Learning(Eds:M.Meila T.Zhang) arXiv preprint arXiv:2405.19716. Vol139 PMLR2021 pp.4904\u20134916."},{"key":"e_1_2_11_17_1","first-page":"8765","volume-title":"Advances in Neural Information Processing Systems","author":"Chuang C.\u2010Y.","year":"2020"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"Y.Zhang H.Zhu Y.Wang N.Xu X.Li B.Zhao inProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple\u2010Wise Perspective in Angular Space Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022 pp.4892\u20134903.","DOI":"10.18653\/v1\/2022.acl-long.336"},{"key":"e_1_2_11_19_1","unstructured":"Y.Jiang L.Zhang W.Wang Findings of the Association for Computational Linguistics: EMNLP 2022 Association for Computational Linguistics Stroudsburg PA2022 pp.3021\u20133035."},{"key":"e_1_2_11_20_1","unstructured":"A.Naik A.Ravichander N.Sadeh C.Rose G.Neubig inProc. of the 27th Inter. Conf. on Computational Linguistics Association for Computational Linguistics Stroudsburg PA2018 pp.2340\u20132353."},{"key":"e_1_2_11_21_1","doi-asserted-by":"crossref","unstructured":"T.Chien J.Kalita inIEEE 14th International Conference on Semantic Computing (ICSC)Adversarial Analysis of Natural Language Inference Systems IEEE Piscataway NJ2020 pp.1\u20138.","DOI":"10.1109\/ICSC.2020.00008"},{"key":"e_1_2_11_22_1","unstructured":"J.Chen Z.Yang D.Yang inProc. of the 58th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Stroudsburg PA2020 pp.2147\u20132157."},{"key":"e_1_2_11_23_1","first-page":"313","volume":"19","author":"Marcus M. P.","year":"1993","journal-title":"Comput. Linguist."},{"key":"e_1_2_11_24_1","unstructured":"X.Zhou M.Bansal inProc. of the 58th Annual Meeting of the Association for Computational Linguistics Association for Computational Linguistics Stroudsburg PA2020 pp.8759\u20138771."},{"key":"e_1_2_11_25_1","first-page":"6256","volume-title":"Advances in Neural Information Processing Systems","author":"Xie Q.","year":"2020"},{"key":"e_1_2_11_26_1","unstructured":"Z.Li L.Specia inProc. of the 5th Workshop on Noisy User\u2010generated Text (W\u2010NUT 2019) Association for Computational Linguistics Stroudsburg PA2019 pp.328\u2013336."},{"key":"e_1_2_11_27_1","unstructured":"E.Agirre C.Banea C.Cardie D.Cer M.Diab A.Gonzalez\u2010Agirre W.Guo I.Lopez\u2010Gazpio M.Maritxalar R.Mihalcea G.Rigau L.Uria J.Wiebe inProc. of the 9th Inter. Workshop on Semantic Evaluation (SemEval 2015) Association for Computational Linguistics Stroudsburg PA2015 pp.252\u2013263."},{"key":"e_1_2_11_28_1","unstructured":"E.Agirre C.Banea C.Cardie D.Cer M.Diab A.Gonzalez\u2010Agirre W.Guo R.Mihalcea G.Rigau J.Wiebe inProc. of the 8th Inter. Workshop on Semantic Evaluation (SemEval 2014) Association for Computational Linguistics Stroudsburg PA2014 pp.81\u201391."},{"key":"e_1_2_11_29_1","unstructured":"E.Agirre C.Banea D.Cer M.Diab A.Gonzalez\u2010Agirre R.Mihalcea G.Rigau J.Wiebe. inProc. of the 10th Inter. Workshop on Semantic Evaluation (SemEval\u20102016) Association for Computational Linguistics Stroudsburg PA2016 pp.497\u2013511."},{"key":"e_1_2_11_30_1","unstructured":"E.Agirre D.Cer M.Diab A.Gonzalez\u2010Agirre in*SEM 2012: The First Joint Conf. on Lexi\u2010 cal and Computational Semantics \u2013 Volume 1: Proceedings of the Main Conference and the Shared Task and Volume 2: Proceedings of the Sixth Inter. Workshop on Semantic Evaluation (SemEval 2012) Association for Computational Linguistics Stroudsburg PA2012 pp.385\u2013393."},{"key":"e_1_2_11_31_1","unstructured":"E.Agirre D.Cer M.Diab A.Gonzalez\u2010Agirre W.\u2010W.Guo inSecond Joint Conf. on Lexical and Computational Semantics (*SEM) Volume 1: Proceedings of the Main Conf. and the Shared Task: Semantic Textual Similarity Association for Computational Linguistics Stroudsburg PA2013 pp.32\u201343."},{"key":"e_1_2_11_32_1","unstructured":"D.Cer M.Diab E.Agirre I.Lopez\u2010Gazpio L.Specia inProc. of the 11th Inter. Workshop on Semantic Evaluation (SemEval\u20102017) Association for Computational Linguistics Stroudsburg PA2017 pp.1\u201314."},{"key":"e_1_2_11_33_1","unstructured":"M.Marelli S.Menini M.Baroni L.Bentivogli R.Bernardi R.Zamparelli inProc. of the Ninth Inter. Conf. on Language Resources and Evaluation (LREC\u201914) European Language Resources Association (ELRA) Reykjavik Iceland2014pp.216\u2013223."},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"E. M.Voorhees D. M.Tice inProc. of the 23rd Annual Inter. ACM SIGIR Conf. on Research and Development in Information Retrieval SIGIR \u201900 200\u2013207 Association for Computing Machinery New York NY2000.","DOI":"10.1145\/345508.345577"},{"key":"e_1_2_11_35_1","doi-asserted-by":"crossref","unstructured":"B.Pang L.Lee inProc. of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL\u201004) Barcelona Spain2004 pp.271\u2013278.","DOI":"10.3115\/1218955.1218990"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"R.Socher A.Perelygin J.Wu J.Chuang C. D.Manning A.Ng C.Potts inProc. of the 2013 Conf. on Empirical Methods in Natural Language Processing Association for Computational Linguistics Stroudsburg PA2013 pp.1631\u20131642.","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_2_11_37_1","unstructured":"W. B.Dolan C.Brockett in Automatically Constructing a Corpus of Sentential Paraphrases.Proc. of the Third Inter. Workshop on Paraphrasing (IWP2005) 2005.https:\/\/aclanthology.org\/I05-5002."},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"B.Pang L.Lee inProc. of the 43rd Annual Meeting of the Associa\u2010 tion for Computational Linguistics (ACL\u201905) Association for Computational Linguistics Stroudsburg PA2005 pp.115\u2013124.","DOI":"10.3115\/1219840.1219855"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-005-7880-9"},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"M.Hu B.Liu inProc. of the Tenth ACM SIGKDD Inter. Conf. on Knowledge Discovery and Data Mining KDD \u201904 Association for Computing Machinery New York NY2004 pp.168\u2013177.","DOI":"10.1145\/1014052.1014073"},{"volume-title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations, Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)","year":"2018","author":"Conneau A.","key":"e_1_2_11_41_1"},{"key":"e_1_2_11_42_1","unstructured":"N.Reimers I.Gurevych inProc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Inter. Joint Conf. on Natural Language Processing (EMNLP\u2010IJCNLP) Association for Computational Linguistics Stroudsburg PA2019 pp.3982\u20133992."}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202300717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T18:49:31Z","timestamp":1759862971000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202300717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1002\/aisy.202300717"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202300717","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"type":"print","value":"2640-4567"},{"type":"electronic","value":"2640-4567"}],"subject":[],"published":{"date-parts":[[2024,7,15]]},"assertion":[{"value":"2023-10-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2300717"}}