{"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/xsense-learning-sense-separated-sparse","title":"xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks","arxiv_id":"1809.03348","date":"2018-09-10","proceeding":null,"authors":["Ting-Yun Chang","Ta-Chung Chi","Shang-Chi Tsai","Yun-Nung Chen"],"abstract":"Despite the success achieved on various natural language processing tasks,\nword embeddings are difficult to interpret due to the dense vector\nrepresentations. This paper focuses on interpreting the embeddings for various\naspects, including sense separation in the vector dimensions and definition\ngeneration. Specifically, given a context together with a target word, our\nalgorithm first projects the target word embedding to a high-dimensional sparse\nvector and picks the specific dimensions that can best explain the semantic\nmeaning of the target word by the encoded contextual information, where the\nsense of the target word can be indirectly inferred. Finally, our algorithm\napplies an RNN to generate the textual definition of the target word in the\nhuman readable form, which enables direct interpretation of the corresponding\nword embedding. This paper also introduces a large and high-quality\ncontext-definition dataset that consists of sense definitions together with\nmultiple example sentences per polysemous word, which is a valuable resource\nfor definition modeling and word sense disambiguation. The conducted\nexperiments show the superior performance in BLEU score and the human\nevaluation test.","url_abs":"http://arxiv.org/abs/1809.03348v1","url_pdf":"http://arxiv.org/pdf/1809.03348v1.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":"xsense-learning-sense-separated-sparse","repo_url":"https://github.com/MiuLab/xSense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03348","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}