{"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/robust-lexical-features-for-improved-neural","title":"Robust Lexical Features for Improved Neural Network Named-Entity Recognition","arxiv_id":"1806.03489","date":"2018-06-09","proceeding":"COLING 2018 8","authors":["Abbas Ghaddar","Philippe Langlais"],"abstract":"Neural network approaches to Named-Entity Recognition reduce the need for\ncarefully hand-crafted features. While some features do remain in\nstate-of-the-art systems, lexical features have been mostly discarded, with the\nexception of gazetteers. In this work, we show that this is unfair: lexical\nfeatures are actually quite useful. We propose to embed words and entity types\ninto a low-dimensional vector space we train from annotated data produced by\ndistant supervision thanks to Wikipedia. From this, we compute - offline - a\nfeature vector representing each word. When used with a vanilla recurrent\nneural network model, this representation yields substantial improvements. We\nestablish a new state-of-the-art F1 score of 87.95 on ONTONOTES 5.0, while\nmatching state-of-the-art performance with a F1 score of 91.73 on the\nover-studied CONLL-2003 dataset.","url_abs":"http://arxiv.org/abs/1806.03489v1","url_pdf":"http://arxiv.org/pdf/1806.03489v1.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":"robust-lexical-features-for-improved-neural","repo_url":"https://github.com/ghaddarAbs/NER-with-LS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"Bi-LSTM-CRF + Lexical Features","rank_in_archive_order":55,"of":73,"metrics":{"F1":"91.73"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"Bi-LSTM-CRF + Lexical Features","rank_in_archive_order":23,"of":28,"metrics":{"F1":"87.95"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03489","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}