{"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/improving-context-aware-language-models","title":"Improving Context Aware Language Models","arxiv_id":"1704.06380","date":"2017-04-21","proceeding":null,"authors":["Aaron Jaech","Mari Ostendorf"],"abstract":"Increased adaptability of RNN language models leads to improved predictions\nthat benefit many applications. However, current methods do not take full\nadvantage of the RNN structure. We show that the most widely-used approach to\nadaptation (concatenating the context with the word embedding at the input to\nthe recurrent layer) is outperformed by a model that has some low-cost\nimprovements: adaptation of both the hidden and output layers. and a feature\nhashing bias term to capture context idiosyncrasies. Experiments on language\nmodeling and classification tasks using three different corpora demonstrate the\nadvantages of the proposed techniques.","url_abs":"http://arxiv.org/abs/1704.06380v1","url_pdf":"http://arxiv.org/pdf/1704.06380v1.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":"improving-context-aware-language-models","repo_url":"https://github.com/ajaech/calm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}