{"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/construction-of-a-japanese-word-similarity","title":"Construction of a Japanese Word Similarity Dataset","arxiv_id":"1703.05916","date":"2017-03-17","proceeding":"LREC 2018 5","authors":["Yuya Sakaizawa","Mamoru Komachi"],"abstract":"An evaluation of distributed word representation is generally conducted using\na word similarity task and/or a word analogy task. There are many datasets\nreadily available for these tasks in English. However, evaluating distributed\nrepresentation in languages that do not have such resources (e.g., Japanese) is\ndifficult. Therefore, as a first step toward evaluating distributed\nrepresentations in Japanese, we constructed a Japanese word similarity dataset.\nTo the best of our knowledge, our dataset is the first resource that can be\nused to evaluate distributed representations in Japanese. Moreover, our dataset\ncontains various parts of speech and includes rare words in addition to common\nwords.","url_abs":"http://arxiv.org/abs/1703.05916v2","url_pdf":"http://arxiv.org/pdf/1703.05916v2.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":"construction-of-a-japanese-word-similarity","repo_url":"https://github.com/tmu-nlp/JapaneseWordSimilarityDataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"construction-of-a-japanese-word-similarity","repo_url":"https://github.com/kdrl/SCNE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"datasets_introduced":[{"slug":"japanese-word-similarity","name":"Japanese Word Similarity","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.05916","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}