{"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/generalizing-word-embeddings-using-bag-of","title":"Generalizing Word Embeddings using Bag of Subwords","arxiv_id":"1809.04259","date":"2018-09-12","proceeding":"EMNLP 2018 10","authors":["Jinman Zhao","Sidharth Mudgal","YIngyu Liang"],"abstract":"We approach the problem of generalizing pre-trained word embeddings beyond\nfixed-size vocabularies without using additional contextual information. We\npropose a subword-level word vector generation model that views words as bags\nof character $n$-grams. The model is simple, fast to train and provides good\nvectors for rare or unseen words. Experiments show that our model achieves\nstate-of-the-art performances in English word similarity task and in joint\nprediction of part-of-speech tag and morphosyntactic attributes in 23\nlanguages, suggesting our model's ability in capturing the relationship between\nwords' textual representations and their embeddings.","url_abs":"http://arxiv.org/abs/1809.04259v1","url_pdf":"http://arxiv.org/pdf/1809.04259v1.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":"generalizing-word-embeddings-using-bag-of","repo_url":"https://github.com/jmzhao/bag-of-substring-embedder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"tag","task_name":"TAG"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.04259","atlas_url":"https://app.syntology.ai/?focus=1809.04259","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}