{"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/russian-word-sense-induction-by-clustering","title":"Russian word sense induction by clustering averaged word embeddings","arxiv_id":"1805.02258","date":"2018-05-06","proceeding":null,"authors":["Andrey Kutuzov"],"abstract":"The paper reports our participation in the shared task on word sense\ninduction and disambiguation for the Russian language (RUSSE-2018). Our team\nwas ranked 2nd for the wiki-wiki dataset (containing mostly homonyms) and 5th\nfor the bts-rnc and active-dict datasets (containing mostly polysemous words)\namong all 19 participants.\n  The method we employed was extremely naive. It implied representing contexts\nof ambiguous words as averaged word embedding vectors, using off-the-shelf\npre-trained distributional models. Then, these vector representations were\nclustered with mainstream clustering techniques, thus producing the groups\ncorresponding to the ambiguous word senses. As a side result, we show that word\nembedding models trained on small but balanced corpora can be superior to those\ntrained on large but noisy data - not only in intrinsic evaluation, but also in\ndownstream tasks like word sense induction.","url_abs":"http://arxiv.org/abs/1805.02258v1","url_pdf":"http://arxiv.org/pdf/1805.02258v1.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":"russian-word-sense-induction-by-clustering","repo_url":"https://github.com/akutuzov/russian_wsi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-sense-induction","task_name":"Word Sense Induction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}