{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/semantic-relation-classification-via-1","title":"Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing","arxiv_id":"1901.08163","date":"2019-01-23","proceeding":null,"authors":["Joohong Lee","Sangwoo Seo","Yong Suk Choi"],"abstract":"Classifying semantic relations between entity pairs in sentences is an\nimportant task in Natural Language Processing (NLP). Most previous models for\nrelation classification rely on the high-level lexical and syntactic features\nobtained by NLP tools such as WordNet, dependency parser, part-of-speech (POS)\ntagger, and named entity recognizers (NER). In addition, state-of-the-art\nneural models based on attention mechanisms do not fully utilize information of\nentity that may be the most crucial features for relation classification. To\naddress these issues, we propose a novel end-to-end recurrent neural model\nwhich incorporates an entity-aware attention mechanism with a latent entity\ntyping (LET) method. Our model not only utilizes entities and their latent\ntypes as features effectively but also is more interpretable by visualizing\nattention mechanisms applied to our model and results of LET. Experimental\nresults on the SemEval-2010 Task 8, one of the most popular relation\nclassification task, demonstrate that our model outperforms existing\nstate-of-the-art models without any high-level features.","url_abs":"http://arxiv.org/abs/1901.08163v1","url_pdf":"http://arxiv.org/pdf/1901.08163v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"semantic-relation-classification-via-1","repo_url":"https://github.com/NEUNLP-RE/Entity-aware-RC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"semantic-relation-classification-via-1","repo_url":"https://github.com/levubk/AEPA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"semantic-relation-classification-via-1","repo_url":"https://github.com/roomylee/entity-aware-relation-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"pos","task_name":"POS"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-semeval-2010-task-8","task":"Relation Extraction","dataset":"SemEval-2010 Task-8","model":"Entity Attention Bi-LSTM","rank_in_archive_order":25,"of":31,"metrics":{"F1":"85.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08163","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}