{"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/joint-word-representation-learning-using-a","title":"Joint Word Representation Learning using a Corpus and a Semantic Lexicon","arxiv_id":"1511.06438","date":"2015-11-19","proceeding":null,"authors":["Danushka Bollegala","Alsuhaibani Mohammed","Takanori Maehara","Ken-ichi Kawarabayashi"],"abstract":"Methods for learning word representations using large text corpora have\nreceived much attention lately due to their impressive performance in numerous\nnatural language processing (NLP) tasks such as, semantic similarity\nmeasurement, and word analogy detection. Despite their success, these\ndata-driven word representation learning methods do not consider the rich\nsemantic relational structure between words in a co-occurring context. On the\nother hand, already much manual effort has gone into the construction of\nsemantic lexicons such as the WordNet that represent the meanings of words by\ndefining the various relationships that exist among the words in a language. We\nconsider the question, can we improve the word representations learnt using a\ncorpora by integrating the knowledge from semantic lexicons?. For this purpose,\nwe propose a joint word representation learning method that simultaneously\npredicts the co-occurrences of two words in a sentence subject to the\nrelational constrains given by the semantic lexicon. We use relations that\nexist between words in the lexicon to regularize the word representations\nlearnt from the corpus. Our proposed method statistically significantly\noutperforms previously proposed methods for incorporating semantic lexicons\ninto word representations on several benchmark datasets for semantic similarity\nand word analogy.","url_abs":"http://arxiv.org/abs/1511.06438v1","url_pdf":"http://arxiv.org/pdf/1511.06438v1.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":"joint-word-representation-learning-using-a","repo_url":"https://github.com/Bollegala/jointreps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06438","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}