{"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/wordrank-learning-word-embeddings-via-robust","title":"WordRank: Learning Word Embeddings via Robust Ranking","arxiv_id":"1506.02761","date":"2015-06-09","proceeding":"EMNLP 2016 11","authors":["Shihao Ji","Hyokun Yun","Pinar Yanardag","Shin Matsushima","S. V. N. Vishwanathan"],"abstract":"Embedding words in a vector space has gained a lot of attention in recent\nyears. While state-of-the-art methods provide efficient computation of word\nsimilarities via a low-dimensional matrix embedding, their motivation is often\nleft unclear. In this paper, we argue that word embedding can be naturally\nviewed as a ranking problem due to the ranking nature of the evaluation\nmetrics. Then, based on this insight, we propose a novel framework WordRank\nthat efficiently estimates word representations via robust ranking, in which\nthe attention mechanism and robustness to noise are readily achieved via the\nDCG-like ranking losses. The performance of WordRank is measured in word\nsimilarity and word analogy benchmarks, and the results are compared to the\nstate-of-the-art word embedding techniques. Our algorithm is very competitive\nto the state-of-the- arts on large corpora, while outperforms them by a\nsignificant margin when the training set is limited (i.e., sparse and noisy).\nWith 17 million tokens, WordRank performs almost as well as existing methods\nusing 7.2 billion tokens on a popular word similarity benchmark. Our multi-node\ndistributed implementation of WordRank is publicly available for general usage.","url_abs":"http://arxiv.org/abs/1506.02761v4","url_pdf":"http://arxiv.org/pdf/1506.02761v4.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":"wordrank-learning-word-embeddings-via-robust","repo_url":"https://bitbucket.org/shihaoji/wordrank","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"wordrank-learning-word-embeddings-via-robust","repo_url":"https://github.com/shihaoji/wordrank","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"learning-word-embeddings","task_name":"Learning Word Embeddings"},{"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":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}