{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:47:05Z","timestamp":1761598025624},"reference-count":4,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2018,12]]},"abstract":"<jats:p> A context-aware language model uses location, user and\/or domain metadata (context) to adapt its predictions. In neural language models, context information is typically represented as an embedding and it is given to the RNN as an additional input, which has been shown to be useful in many applications. We introduce a more powerful mechanism for using context to adapt an RNN by letting the context vector control a low-rank transformation of the recurrent layer weight matrix. Experiments show that allowing a greater fraction of the model parameters to be adjusted has benefits in terms of perplexity and classification for several different types of context. <\/jats:p>","DOI":"10.1162\/tacl_a_00035","type":"journal-article","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T19:32:50Z","timestamp":1544470370000},"page":"497-510","source":"Crossref","is-referenced-by-count":8,"title":["Low-Rank RNN Adaptation for Context-Aware Language Modeling"],"prefix":"10.1162","volume":"6","author":[{"given":"Aaron","family":"Jaech","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of Washington, 185 Stevens Way, Paul Allen Center AE100R, Seattle, WA,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mari","family":"Ostendorf","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Washington, 185 Stevens Way, Paul Allen Center AE100R, Seattle, WA,"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"issue":"1","key":"p_2","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.specom.2003.08.002","volume":"42","author":"Bellegarda Jerome R.","year":"2004","journal-title":"Speech Communication"},{"issue":"3","key":"p_14","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1109\/TASLP.2014.2379593","volume":"23","author":"Hutchinson Brian","year":"2015","journal-title":"IEEE Trans. Audio, Speech and Language Processing"},{"key":"p_30","first-page":"1757","author":"Semeniuta Stanislau","year":"2016","journal-title":"Proc. Int. Conf. Computational Linguistics (COLING), pages"},{"key":"p_35","first-page":"649","author":"Zhang Xiang","year":"2015","journal-title":"Proc. Annu. Conf. Neural Inform. Process. Syst. (NIPS), pages"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:01Z","timestamp":1615585081000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":4,"alternative-id":["10.1162\/tacl_a_00035"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00035","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}