{"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/context-encoders-as-a-simple-but-powerful","title":"Context encoders as a simple but powerful extension of word2vec","arxiv_id":"1706.02496","date":"2017-06-08","proceeding":"WS 2017 8","authors":["Franziska Horn"],"abstract":"With a simple architecture and the ability to learn meaningful word\nembeddings efficiently from texts containing billions of words, word2vec\nremains one of the most popular neural language models used today. However, as\nonly a single embedding is learned for every word in the vocabulary, the model\nfails to optimally represent words with multiple meanings. Additionally, it is\nnot possible to create embeddings for new (out-of-vocabulary) words on the\nspot. Based on an intuitive interpretation of the continuous bag-of-words\n(CBOW) word2vec model's negative sampling training objective in terms of\npredicting context based similarities, we motivate an extension of the model we\ncall context encoders (ConEc). By multiplying the matrix of trained word2vec\nembeddings with a word's average context vector, out-of-vocabulary (OOV)\nembeddings and representations for a word with multiple meanings can be created\nbased on the word's local contexts. The benefits of this approach are\nillustrated by using these word embeddings as features in the CoNLL 2003 named\nentity recognition (NER) task.","url_abs":"http://arxiv.org/abs/1706.02496v1","url_pdf":"http://arxiv.org/pdf/1706.02496v1.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":"context-encoders-as-a-simple-but-powerful","repo_url":"https://github.com/cod3licious/conec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"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}