{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T06:35:12Z","timestamp":1780468512285,"version":"3.54.1"},"reference-count":48,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2022,3,3]],"date-time":"2022-03-03T00:00:00Z","timestamp":1646265600000},"content-version":"vor","delay-in-days":61,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Relational extraction plays an important role in the field of natural language processing to predict semantic relationships between entities in a sentence. Currently, most models have typically utilized the natural language processing tools to capture high-level features with an attention mechanism to mitigate the adverse effects of noise in sentences for the prediction results. However, in the task of relational classification, these attention mechanisms do not take full advantage of the semantic information of some keywords which have information on relational expressions in the sentences. Therefore, we propose a novel relation extraction model based on the attention mechanism with keywords, named Relation Extraction Based on Keywords Attention (REKA). In particular, the proposed model makes use of bi-directional GRU (Bi-GRU) to reduce computation, obtain the representation of sentences, and extracts prior knowledge of entity pair without any NLP tools. Besides the calculation of the entity-pair similarity, Keywords attention in the REKA model also utilizes a linear-chain conditional random field (CRF) combining entity-pair features, similarity features between entity-pair features, and its hidden vectors, to obtain the attention weight resulting from the marginal distribution of each word. Experiments demonstrate that the proposed approach can utilize keywords incorporating relational expression semantics in sentences without the assistance of any high-level features and achieve better performance than traditional methods.<\/jats:p>","DOI":"10.1162\/dint_a_00147","type":"journal-article","created":{"date-parts":[[2022,3,3]],"date-time":"2022-03-03T14:00:57Z","timestamp":1646316057000},"page":"552-572","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":9,"title":["Bi-GRU Relation Extraction Model Based on Keywords\n                    Attention"],"prefix":"10.3724","volume":"4","author":[{"given":"Yuanyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Technical Training Center of State Grid Hubei Electric Power Co., Ltd. Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Hubei University of Technology, School of Computer Science, Wuhan 430068, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengkang","family":"Yu","sequence":"additional","affiliation":[{"name":"Technical Training Center of State Grid Hubei Electric Power Co., Ltd. Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqin","family":"Gu","sequence":"additional","affiliation":[{"name":"Technical Training Center of State Grid Hubei Electric Power Co., Ltd. Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengqiong","family":"Song","sequence":"additional","affiliation":[{"name":"Technical Training Center of State Grid Hubei Electric Power Co., Ltd. Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Peng","sequence":"additional","affiliation":[{"name":"Technical Training Center of State Grid Hubei Electric Power Co., Ltd. Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxia","family":"Chen","sequence":"additional","affiliation":[{"name":"Hubei University of Technology, School of Computer Science, Wuhan 430068, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Hubei University of Technology, School of Computer Science, Wuhan 430068, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2022,7,1]]},"reference":[{"key":"2022081019142837700_ref1","first-page":"1247","volume-title":"Free-base: a collaboratively created graph database for structuring\n                        human knowledge","author":"Bollacker","year":"2008,"},{"key":"2022081019142837700_ref2","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","article-title":"Dbpedia: A nucleus for a web of open data","volume-title":"The semantic web","author":"Auer","year":"2007"},{"key":"2022081019142837700_ref3","volume-title":"Relation extraction: A survey","author":"Pawar","year":"2017"},{"key":"2022081019142837700_ref4","first-page":"2335","volume-title":"Relation classification via convolutional deep neural\n                        network","author":"Zeng","year":"2014,"},{"key":"2022081019142837700_ref5","first-page":"1785","volume-title":"Classifying relations via long short term memory networks along\n                        shortest dependency paths","author":"Xu","year":"2015,"},{"key":"2022081019142837700_ref6","first-page":"231","volume-title":"Convolution neural network for relation extraction","author":"Liu","year":"2013,"},{"key":"2022081019142837700_ref7","first-page":"39","volume-title":"Relation extraction: Perspective from convolutional neural\n                        networks","author":"Nguyen","year":"2015,"},{"key":"2022081019142837700_ref8","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P15-1061","volume-title":"Classifying relations by ranking with convolutional neural\n                        networks","author":"Santos","year":"2015"},{"key":"2022081019142837700_ref9","volume-title":"Convolutional neural network for sentence classification","author":"Chen","year":"2015"},{"key":"2022081019142837700_ref10","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P14-1062","volume-title":"A convolutional neural network for modelling sentences","author":"Kalchbrenner","year":"2014"},{"issue":"2","key":"2022081019142837700_ref11","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/BF00114844","article-title":"Distributed representations, simple recurrent networks, and\n                        grammatical structure","volume":"7","author":"Elman","year":"1991","journal-title":"Machine learning"},{"key":"2022081019142837700_ref12","volume-title":"Relation classification via recurrent neural network","author":"Zhang","year":"2015"},{"key":"2022081019142837700_ref13","first-page":"73","volume-title":"Bidirectional long short-term memory networks for relation\n                        classification","author":"Zhang","year":"2015,"},{"key":"2022081019142837700_ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-65","volume-title":"LSTM\n                        neural networks for language modeling","author":"Sundermeyer","year":"2012"},{"issue":"8","key":"2022081019142837700_ref15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural\n                        computation"},{"key":"2022081019142837700_ref16","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence\n                        modeling","author":"Chung","year":"2014"},{"key":"2022081019142837700_ref17","article-title":"Deep neural network-based relation extraction: an\n                        overview","volume":"1-21","author":"Wang","year":"2022","journal-title":"Neural Computing and\n                        Applications,"},{"key":"2022081019142837700_ref18","first-page":"1785","volume-title":"Classifying relations via long short term memory networks along\n                        shortest dependency paths","author":"Xu","year":"2015,"},{"key":"2022081019142837700_ref19","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1004","volume-title":"Position-aware attention and supervised data improve slot\n                        filling","author":"Zhang","year":"2017"},{"key":"2022081019142837700_ref20","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1244","volume-title":"Graph convolution over pruned dependency trees improves relation\n                        extraction","author":"Zhang","year":"2018"},{"key":"2022081019142837700_ref21","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1243","volume-title":"Neural relation extraction via inner-sentence noise reduction and\n                        transfer learning","author":"Liu","year":"2018"},{"issue":"6","key":"2022081019142837700_ref22","doi-asserted-by":"crossref","first-page":"785","DOI":"10.3390\/sym11060785","article-title":"Semantic relation classification via bidirectional lstm\n                        networks with entity-aware attention using latent entity\n                        typing","volume":"11","author":"Lee","year":"2019","journal-title":"Symmetry"},{"key":"2022081019142837700_ref23","doi-asserted-by":"crossref","first-page":"105928","DOI":"10.1016\/j.knosys.2020.105928","article-title":"Direction-sensitive relation extraction using bi-sdp\n                        attention model","volume":"198","author":"Wang","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"2022081019142837700_ref24","first-page":"5401","volume-title":"Beyond Word Attention: Using Segment Attention in Neural Relation\n                        Extraction","author":"Yu","year":"2019,"},{"key":"2022081019142837700_ref25","volume-title":"Neural relation extraction: a survey","author":"Aydar","year":"2020"},{"key":"2022081019142837700_ref26","first-page":"1201","volume-title":"Semantic compositionality through recursive matrix-vector\n                        spaces","author":"Socher","year":"2012,"},{"key":"2022081019142837700_ref27","first-page":"1753","volume-title":"Distant supervision for relation extraction via piecewise\n                        convolutional neural networks","author":"Zeng","year":"2015,"},{"key":"2022081019142837700_ref28","volume-title":"Relation classification via recurrent neural network","author":"Zhang","year":"2015"},{"key":"2022081019142837700_ref29","volume-title":"Improved relation classification by deep recurrent neural networks\n                        with data augmentation","author":"Xu","year":"2016"},{"key":"2022081019142837700_ref30","first-page":"73","volume-title":"Bidirectional long short-term memory networks for relation\n                        classification","author":"Zhang","year":"2015,"},{"key":"2022081019142837700_ref31","first-page":"207","volume-title":"Attention-based bidirectional long short-term memory networks for\n                        relation classification","author":"Zhou","year":"2016,"},{"key":"2022081019142837700_ref32","first-page":"1254","volume-title":"Semantic relation classification via hierarchical recurrent neural\n                        network with attention","author":"Xiao","year":"2016,"},{"key":"2022081019142837700_ref33","first-page":"4356","volume-title":"Designing an adaptive attention mechanism for relation\n                        classification","author":"Qin","year":"2017,"},{"key":"2022081019142837700_ref34","doi-asserted-by":"crossref","first-page":"5343","DOI":"10.1109\/ACCESS.2018.2888508","article-title":"Multi-gram CNN-based self-attention model for relation\n                        classification","volume":"7","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"2022081019142837700_ref35","doi-asserted-by":"crossref","first-page":"5343","DOI":"10.1109\/ACCESS.2018.2888508","article-title":"Multi-gram CNN-based self-attention model for relation\n                        classification","volume":"7","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"2022081019142837700_ref36","volume-title":"A\n                        novel cascade binary tagging framework for relational triple\n                        extraction","author":"Wei","year":"2019"},{"key":"2022081019142837700_ref37","first-page":"1003","volume-title":"Distant supervision for relation extraction without labeled\n                        data","author":"Mintz","year":"2009,"},{"issue":"5","key":"2022081019142837700_ref38","doi-asserted-by":"crossref","first-page":"2933","DOI":"10.1007\/s11280-020-00816-9","article-title":"End-to-end relation extraction based on bootstrapped\n                        multi-level distant supervision","volume":"23","author":"He","year":"2020","journal-title":"World Wide\n                        Web"},{"issue":"1","key":"2022081019142837700_ref39","article-title":"Neural knowledge acquisition via mutual attention between\n                        knowledge graph and text","volume":"32","author":"Han","year":"2018,","journal-title":"In: Proceedings of the\n                        AAAI Conference on Artificial Intelligence"},{"key":"2022081019142837700_ref40","first-page":"2246","volume-title":"Label-free distant supervision for relation extraction via knowledge\n                        graph embedding","author":"Wang","year":"2018"},{"key":"2022081019142837700_ref41","volume-title":"Efficient estimation of word representations in vector\n                        space","author":"Mikolov","year":"2013"},{"key":"2022081019142837700_ref42","first-page":"1532","volume-title":"Glove: Global vectors for word representation","author":"Pennington","year":"2014,"},{"key":"2022081019142837700_ref43","doi-asserted-by":"crossref","first-page":"114135","DOI":"10.1016\/j.psychres.2021.114135","article-title":"Detecting formal thought disorder by deep contextualized word\n                        representations","volume":"304","author":"Sarzynska-Wawer","year":"2021","journal-title":"Psychiatry Research"},{"key":"2022081019142837700_ref44","first-page":"256","volume-title":"Utd: Classifying semantic relations by combining lexical and\n                        semantic resources","author":"Rink","year":"2010,"},{"key":"2022081019142837700_ref45","first-page":"1201","volume-title":"Semantic compositionality through recursive matrix-vector\n                        spaces","author":"Socher","year":"2012,"},{"key":"2022081019142837700_ref46","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P15-2047","volume-title":"A\n                        dependency-based neural network for relation classification","author":"Liu","year":"2015"},{"key":"2022081019142837700_ref47","volume-title":"Position-aware self-attention with relative positional encodings for\n                        slot filling","author":"Bilan","year":"2018"},{"key":"2022081019142837700_ref48","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1132","volume-title":"Extracting multiple-relations in one-pass with pre-trained\n                        transformers","author":"Wang","year":"2019"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/4\/3\/552\/2038412\/dint_a_00147.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/4\/3\/552\/2038412\/dint_a_00147.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:41:20Z","timestamp":1741938080000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00147","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}