{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T22:00:23Z","timestamp":1747173623680,"version":"3.40.5"},"reference-count":44,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In recent years, the extraction of overlapping relations has received great attention in the field of natural language processing (NLP). However, most existing approaches treat relational triples in sentences as isolated, without considering the rich semantic correlations implied in the relational hierarchy. Extracting these overlapping relational triples is challenging, given the overlapping types are various and relatively complex. In addition, these approaches do not highlight the semantic information in the sentence from coarse-grained to fine-grained. In this paper, we propose an end-to-end neural framework based on a decomposition model that incorporates multi-granularity relational features for the extraction of overlapping triples. Our approach employs an attention mechanism that combines relational hierarchy information with multiple granularities and pretrained textual representations, where the relational hierarchies are constructed manually or obtained by unsupervised clustering. We found that the different hierarchy construction strategies have little effect on the final extraction results. Experimental results on two public datasets, NYT and WebNLG, show that our mode substantially outperforms the baseline system in extracting overlapping relational triples, especially for long-tailed relations.<\/jats:p>","DOI":"10.1017\/s1351324923000050","type":"journal-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T10:45:34Z","timestamp":1676976334000},"page":"1126-1149","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":0,"title":["An end-to-end neural framework using coarse-to-fine-grained attention for overlapping relational triple extraction"],"prefix":"10.1017","volume":"29","author":[{"given":"Huizhe","family":"Su","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9828","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"S1351324923000050_ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247938"},{"key":"S1351324923000050_ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15939-8_10"},{"key":"S1351324923000050_ref34","doi-asserted-by":"crossref","unstructured":"Zeng, D. , Zhang, H. and Liu, Q. (2020). Copymtl: Copy mechanism for joint extraction of entities and relations with multi-task learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):9507\u20139514.","DOI":"10.1609\/aaai.v34i05.6495"},{"key":"S1351324923000050_ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.486"},{"key":"S1351324923000050_ref31","unstructured":"Yu, B. , Zhang, Z. , Shu, X. , Wang, Y. , Liu, T. , Wang, B. and Li, S. (2020). Joint extraction of entities and relations based on a novel decomposition strategy. In ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), 325:2282\u20132289."},{"key":"S1351324923000050_ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"S1351324923000050_ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.136"},{"key":"S1351324923000050_ref28","unstructured":"Xiao, L. , Zhou, D. and Wu, M. (2011). Hierarchical classification via orthogonal transfer. In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011, pp. 801\u2013808."},{"key":"S1351324923000050_ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1047"},{"key":"S1351324923000050_ref37","first-page":"3016","article-title":"Long-tail relation extraction via knowledge graph embeddings and graph convolution networks","author":"Zhang","year":"2019","journal-title":"Association for Computational Linguistics"},{"key":"S1351324923000050_ref41","unstructured":"Zhao, B. , Li, F.-F. and Xing, P.E. (2011). Large-scale category structure aware image categorization. In NIPS, 1251\u20131259."},{"key":"S1351324923000050_ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1205"},{"key":"S1351324923000050_ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115806"},{"key":"S1351324923000050_ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1055"},{"key":"S1351324923000050_ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.07.032"},{"key":"S1351324923000050_ref9","unstructured":"Gupta, P. , Sch\u00fctze, H. and Andrassy, B. (2016). Table filling multi-task recurrent neural network for joint entity and relation extraction. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2537\u20132547."},{"key":"S1351324923000050_ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.1136800"},{"key":"S1351324923000050_ref2","unstructured":"Bi, W. and Kwok, J.T. (2011). Multilabel classification on tree-and dag-structured hierarchies. In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011, pp. 17\u201324."},{"key":"S1351324923000050_ref15","first-page":"1","article-title":"Distantly-supervised long-tailed relation extraction using constraint graphs","author":"Liang","year":"2021","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"S1351324923000050_ref11","first-page":"1292","article-title":"Entity hierarchy embedding","author":"Hu","year":"2015","journal-title":"The Association for Computer Linguistics"},{"key":"S1351324923000050_ref29","first-page":"2965","article-title":"Representation learning of knowledge graphs with hierarchical types","author":"Xie","year":"2016","journal-title":"IJCAI"},{"key":"S1351324923000050_ref16","first-page":"359","article-title":"Improving text classification by shrinkage in a hierarchy of classes","volume":"98","author":"McCallum","year":"1998","journal-title":"ICML"},{"key":"S1351324923000050_ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.138"},{"key":"S1351324923000050_ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1200"},{"key":"S1351324923000050_ref14","first-page":"1653","article-title":"Improving long-tail relation extraction with collaborating relation-augmented attention","author":"Li","year":"2020","journal-title":"COLING"},{"key":"S1351324923000050_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1035"},{"key":"S1351324923000050_ref12","unstructured":"Kai, S. , Richong, Z. , Samuel, M. , Yongyi, M. and Xudong, L. (2020). Recurrent interaction network for jointly extracting entities and classifying relations. In EMNLP 2020, pp. 3722\u20133732."},{"key":"S1351324923000050_ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102445"},{"key":"S1351324923000050_ref32","first-page":"1399","article-title":"Jointly identifying entities and extracting relations in encyclopedia text via a graphical model approach","author":"Yu","year":"2010","journal-title":"Coling 2010: Posters"},{"key":"S1351324923000050_ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1247"},{"key":"S1351324923000050_ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052708"},{"key":"S1351324923000050_ref27","unstructured":"Weinberger, K.Q. and Chapelle, O. (2009). Large margin taxonomy embedding for document categorization. In Advances in Neural Information Processing Systems, pp. 1737\u20131744."},{"key":"S1351324923000050_ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1358"},{"key":"S1351324923000050_ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1017"},{"key":"S1351324923000050_ref4","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"Association for Computational Linguistics"},{"key":"S1351324923000050_ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1136"},{"key":"S1351324923000050_ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017072"},{"key":"S1351324923000050_ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17677"},{"key":"S1351324923000050_ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3110126"},{"key":"S1351324923000050_ref44","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016728"},{"key":"S1351324923000050_ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1113"},{"key":"S1351324923000050_ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1038"},{"key":"S1351324923000050_ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6374"},{"key":"S1351324923000050_ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/561"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324923000050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T08:59:39Z","timestamp":1689757179000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324923000050\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["S1351324923000050"],"URL":"https:\/\/doi.org\/10.1017\/s1351324923000050","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"type":"print","value":"1351-3249"},{"type":"electronic","value":"1469-8110"}],"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"\u00a9 The Author(s), 2023. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}