{"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/improved-relation-extraction-with-feature","title":"Improved Relation Extraction with Feature-Rich Compositional Embedding Models","arxiv_id":"1505.02419","date":"2015-05-10","proceeding":"EMNLP 2015 9","authors":["Matthew R. Gormley","Mo Yu","Mark Dredze"],"abstract":"Compositional embedding models build a representation (or embedding) for a\nlinguistic structure based on its component word embeddings. We propose a\nFeature-rich Compositional Embedding Model (FCM) for relation extraction that\nis expressive, generalizes to new domains, and is easy-to-implement. The key\nidea is to combine both (unlexicalized) hand-crafted features with learned word\nembeddings. The model is able to directly tackle the difficulties met by\ntraditional compositional embeddings models, such as handling arbitrary types\nof sentence annotations and utilizing global information for composition. We\ntest the proposed model on two relation extraction tasks, and demonstrate that\nour model outperforms both previous compositional models and traditional\nfeature rich models on the ACE 2005 relation extraction task, and the SemEval\n2010 relation classification task. The combination of our model and a\nlog-linear classifier with hand-crafted features gives state-of-the-art\nresults.","url_abs":"http://arxiv.org/abs/1505.02419v3","url_pdf":"http://arxiv.org/pdf/1505.02419v3.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":"improved-relation-extraction-with-feature","repo_url":"https://github.com/mgormley/pacaya","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-ace-2005","task":"Relation Extraction","dataset":"ACE 2005","model":"FCM","rank_in_archive_order":28,"of":30,"metrics":{"Cross Sentence":"No","Relation classification F1":"58.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.02419","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}