{"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/word-movers-embedding-from-word2vec-to","title":"Word Mover's Embedding: From Word2Vec to Document Embedding","arxiv_id":"1811.01713","date":"2018-10-30","proceeding":"EMNLP 2018 10","authors":["Lingfei Wu","Ian E. H. Yen","Kun Xu","Fangli Xu","Avinash Balakrishnan","Pin-Yu Chen","Pradeep Ravikumar","Michael J. Witbrock"],"abstract":"While the celebrated Word2Vec technique yields semantically rich\nrepresentations for individual words, there has been relatively less success in\nextending to generate unsupervised sentences or documents embeddings. Recent\nwork has demonstrated that a distance measure between documents called\n\\emph{Word Mover's Distance} (WMD) that aligns semantically similar words,\nyields unprecedented KNN classification accuracy. However, WMD is expensive to\ncompute, and it is hard to extend its use beyond a KNN classifier. In this\npaper, we propose the \\emph{Word Mover's Embedding } (WME), a novel approach to\nbuilding an unsupervised document (sentence) embedding from pre-trained word\nembeddings. In our experiments on 9 benchmark text classification datasets and\n22 textual similarity tasks, the proposed technique consistently matches or\noutperforms state-of-the-art techniques, with significantly higher accuracy on\nproblems of short length.","url_abs":"http://arxiv.org/abs/1811.01713v1","url_pdf":"http://arxiv.org/pdf/1811.01713v1.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":"word-movers-embedding-from-word2vec-to","repo_url":"https://github.com/IBM/WordMoversEmbeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"document-embedding","task_name":"Document Embedding"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.01713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}