{"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/learning-chinese-word-representations-from","title":"Learning Chinese Word Representations From Glyphs Of Characters","arxiv_id":"1708.04755","date":"2017-08-16","proceeding":"EMNLP 2017 9","authors":["Tzu-Ray Su","Hung-Yi Lee"],"abstract":"In this paper, we propose new methods to learn Chinese word representations.\nChinese characters are composed of graphical components, which carry rich\nsemantics. It is common for a Chinese learner to comprehend the meaning of a\nword from these graphical components. As a result, we propose models that\nenhance word representations by character glyphs. The character glyph features\nare directly learned from the bitmaps of characters by convolutional\nauto-encoder(convAE), and the glyph features improve Chinese word\nrepresentations which are already enhanced by character embeddings. Another\ncontribution in this paper is that we created several evaluation datasets in\ntraditional Chinese and made them public.","url_abs":"http://arxiv.org/abs/1708.04755v1","url_pdf":"http://arxiv.org/pdf/1708.04755v1.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":"learning-chinese-word-representations-from","repo_url":"https://github.com/ray1007/GWE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04755","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}