{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T20:40:16Z","timestamp":1734986416985,"version":"3.32.0"},"reference-count":38,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":357,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Relation extraction has evolved from supervised relation extraction to zero-shot setting due to the continuous emergence of newly generated relations. Some pioneering works handle zero-shot relation extraction by reformulating it into proxy tasks, such as reading comprehension and textual entailment. Nonetheless, the divergence in proxy task formulations from relation extraction hinders the acquisition of informative semantic representations, leading to subpar performance. Therefore, in this paper, we take a data-driven view to handle zero-shot relation extraction under a three-step paradigm, including encoder training, relation clustering, and summarization. Specifically, to train a discriminative relational encoder, we propose a novel selective contrastive learning framework, namely, SCL, where selective importance scores are assigned to distinguish the importance of different negative contrastive instances. During testing, the prompt-based encoder is employed to map test samples into representation vectors, which are then clustered into several groups. Typical samples closest to the cluster centroid are selected for summarization to generate the predicted relation for all samples in the cluster. Moreover, we design a simple non-parametric threshold plugin to reduce false-positive errors in inference on unseen relation representations. Our experiments demonstrate that SCL outperforms the current state-of-the-art method by over 3% across all metrics.<\/jats:p>","DOI":"10.1162\/tacl_a_00721","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T20:12:24Z","timestamp":1734984744000},"page":"1720-1735","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["SCL: Selective Contrastive Learning for Data-driven Zero-shot Relation Extraction"],"prefix":"10.1162","volume":"12","author":[{"given":"Ning","family":"Pang","sequence":"first","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, China. pangning14@nudt.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, National University of Defense Technology, China. xiangzhao@nudt.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Laboratory for Big Data and Decision, National University of Defense Technology, China. zengweixin13@nudt.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Tan","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, China. tanzhen08a@nudt.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"Xiao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, China. wdxiao@nudt.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"2024122320121775000_bib1","first-page":"2670","article-title":"Open information extraction from the web","volume-title":"IJCAI","author":"Banko","year":"2007"},{"key":"2024122320121775000_bib2","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1145\/1772690.1772707","article-title":"Relational duality: Unsupervised extraction of semantic relations between entities on the web","volume-title":"WWW","author":"Bollegala","year":"2010"},{"key":"2024122320121775000_bib3","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown","year":"2020"},{"key":"2024122320121775000_bib4","doi-asserted-by":"publisher","first-page":"3470","DOI":"10.18653\/v1\/2021.naacl-main.272","article-title":"ZS-BERT: Towards zero-shot relation extraction with attribute representation learning","volume-title":"NAACL-HLT","author":"Chen","year":"2021"},{"key":"2024122320121775000_bib5","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen","year":"2020"},{"key":"2024122320121775000_bib6","doi-asserted-by":"publisher","first-page":"2778","DOI":"10.1145\/3485447.3511998","article-title":"Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction","volume-title":"WWW","author":"Chen","year":"2022"},{"key":"2024122320121775000_bib7","doi-asserted-by":"publisher","first-page":"45","DOI":"10.18653\/v1\/2022.findings-acl.5","article-title":"Relationprompt: Leveraging prompts to generate synthetic data for zero-shot relation triplet extraction","volume-title":"ACL (Findings)","author":"Chia","year":"2022"},{"key":"2024122320121775000_bib8","doi-asserted-by":"publisher","first-page":"232","DOI":"10.18653\/v1\/2021.acl-long.20","article-title":"Refining sample embeddings with relation prototypes to enhance continual relation extraction","volume-title":"ACL\/IJCNLP (1)","author":"Li","year":"2021"},{"key":"2024122320121775000_bib9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT (1)","author":"Devlin","year":"2019"},{"key":"2024122320121775000_bib10","doi-asserted-by":"publisher","first-page":"6888","DOI":"10.18653\/v1\/2022.findings-emnlp.512","article-title":"Prompt-learning for fine-grained entity typing","volume-title":"EMNLP (Findings)","author":"Ding","year":"2022"},{"key":"2024122320121775000_bib11","first-page":"3816","article-title":"Making pre-trained language models better few-shot learners","volume-title":"ACL\/IJCNLP (1)","author":"Gao","year":"2021"},{"key":"2024122320121775000_bib12","first-page":"6249","article-title":"Fewrel 2.0: Towards more challenging few-shot relation classification","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3\u20137, 2019","author":"Gao","year":"2019"},{"key":"2024122320121775000_bib13","first-page":"6894","article-title":"Simcse: Simple contrastive learning of sentence embeddings","volume-title":"EMNLP (1)","author":"Gao","year":"2021"},{"key":"2024122320121775000_bib14","article-title":"PTR: Prompt tuning with rules for text classification","author":"Han","year":"2021","journal-title":"CoRR"},{"issue":"1","key":"2024122320121775000_bib15","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2307\/2346830","article-title":"Algorithm as 136: A k-means clustering algorithm","volume":"28","author":"Hartigan","year":"1979","journal-title":"Journal of the Royal Statistical Society. Series C (Applied Statistics)"},{"key":"2024122320121775000_bib16","doi-asserted-by":"publisher","first-page":"9726","DOI":"10.1109\/CVPR42600.2020.00975","article-title":"Momentum contrast for unsupervised visual representation learning","volume-title":"CVPR","author":"He","year":"2020"},{"key":"2024122320121775000_bib17","doi-asserted-by":"publisher","first-page":"3673","DOI":"10.18653\/v1\/2020.emnlp-main.299","article-title":"Selfore: Self-supervised relational feature learning for open relation extraction","volume-title":"EMNLP (1)","author":"Xuming","year":"2020"},{"key":"2024122320121775000_bib18","article-title":"Supervised contrastive learning","volume-title":"NeurIPS","author":"Khosla","year":"2020"},{"key":"2024122320121775000_bib19","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR (Poster)","author":"Kingma","year":"2015"},{"key":"2024122320121775000_bib20","doi-asserted-by":"publisher","first-page":"333","DOI":"10.18653\/v1\/K17-1034","article-title":"Zero-shot relation extraction via reading comprehension","volume-title":"CoNLL","author":"Levy","year":"2017"},{"key":"2024122320121775000_bib21","doi-asserted-by":"publisher","first-page":"5970","DOI":"10.18653\/v1\/2022.naacl-main.437","article-title":"Hiure: Hierarchical exemplar contrastive learning for unsupervised relation extraction","volume-title":"NAACL-HLT","author":"Liu","year":"2022"},{"key":"2024122320121775000_bib22","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1109\/MFI49285.2020.9235263","article-title":"A hybrid approach to hierarchical density-based cluster selection","volume-title":"MFI","author":"Malzer","year":"2020"},{"key":"2024122320121775000_bib23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1105","article-title":"End-to-end relation extraction using lstms on sequences and tree structures","volume-title":"ACL (1)","author":"Miwa","year":"2016"},{"key":"2024122320121775000_bib24","doi-asserted-by":"publisher","first-page":"72","DOI":"10.18653\/v1\/W18-5511","article-title":"Zero-shot relation classification as textual entailment","volume-title":"Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)","author":"Obamuyide","year":"2018"},{"key":"2024122320121775000_bib25","article-title":"Introducing chatgpt","author":"OpenAI","year":"2022"},{"key":"2024122320121775000_bib26","first-page":"74","article-title":"Relation extraction with matrix factorization and universal schemas","volume-title":"HLT-NAACL","author":"Riedel","year":"2013"},{"key":"2024122320121775000_bib27","doi-asserted-by":"publisher","first-page":"5569","DOI":"10.18653\/v1\/2020.coling-main.488","article-title":"Automatically identifying words that can serve as labels for few-shot text classification","volume-title":"COLING","author":"Schick","year":"2020"},{"key":"2024122320121775000_bib28","doi-asserted-by":"publisher","first-page":"2895","DOI":"10.18653\/v1\/P19-1279","article-title":"Matching the blanks: Distributional similarity for relation learning","volume-title":"ACL (1)","author":"Soares","year":"2019"},{"key":"2024122320121775000_bib29","doi-asserted-by":"publisher","first-page":"886","DOI":"10.18653\/v1\/N16-1103","article-title":"Multilingual relation extraction using compositional universal schema","volume-title":"HLT-NAACL","author":"Verga","year":"2016"},{"key":"2024122320121775000_bib30","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.18653\/v1\/2022.findings-naacl.188","article-title":"RCL: Relation contrastive learning for zero-shot relation extraction","volume-title":"NAACL-HLT (Findings)","author":"Wang","year":"2022"},{"key":"2024122320121775000_bib31","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"EMNLP (Demos)","author":"Wolf","year":"2020"},{"key":"2024122320121775000_bib32","first-page":"1","article-title":"Zero-shot relation extraction model via multi-template fusion in prompt","author":"Liang","year":"2023","journal-title":"Journal of Computer Applications"},{"key":"2024122320121775000_bib33","doi-asserted-by":"publisher","first-page":"5065","DOI":"10.18653\/v1\/2021.acl-long.393","article-title":"Consert: A contrastive framework for self-supervised sentence representation transfer","volume-title":"ACL\/IJCNLP (1)","author":"Yan","year":"2021"},{"key":"2024122320121775000_bib34","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.18653\/v1\/D15-1203","article-title":"Distant supervision for relation extraction via piecewise convolutional neural networks","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17\u201321, 2015","author":"Zeng","year":"2015"},{"key":"2024122320121775000_bib35","first-page":"2335","article-title":"Relation classification via convolutional deep neural network","volume-title":"COLING 2014, 25th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, August 23\u201329, 2014, Dublin, Ireland","author":"Zeng","year":"2014"},{"key":"2024122320121775000_bib36","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TASLP.2022.3199655","article-title":"Prompt-based prototypical framework for continual relation extraction","volume":"30","author":"Zhang","year":"2022","journal-title":"EEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2024122320121775000_bib37","doi-asserted-by":"publisher","first-page":"35","DOI":"10.18653\/v1\/D17-1004","article-title":"Position-aware attention and supervised data improve slot filling","volume-title":"EMNLP","author":"Zhang","year":"2017"},{"key":"2024122320121775000_bib38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034","article-title":"Attention-based bidirectional long short-term memory networks for relation classification","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7\u201312, 2016, Berlin, Germany, Volume 2: Short Papers","author":"Zhou","year":"2016"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00721\/2487029\/tacl_a_00721.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00721\/2487029\/tacl_a_00721.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T20:12:28Z","timestamp":1734984748000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00721\/125949\/SCL-Selective-Contrastive-Learning-for-Data-driven"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00721","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}