{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:28:16Z","timestamp":1761989296318},"reference-count":5,"publisher":"MIT Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2017,12]]},"abstract":"<jats:p> We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset. <\/jats:p>","DOI":"10.1162\/tacl_a_00077","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T15:42:50Z","timestamp":1546011770000},"page":"515-528","source":"Crossref","is-referenced-by-count":46,"title":["Aspect-augmented Adversarial Networks for Domain                     Adaptation"],"prefix":"10.1162","volume":"5","author":[{"given":"Yuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts                         Institute of Technology,"}]},{"given":"Regina","family":"Barzilay","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts                         Institute of Technology,"}]},{"given":"Tommi","family":"Jaakkola","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts                         Institute of Technology,"}]}],"member":"281","reference":[{"issue":"1","key":"p_6","doi-asserted-by":"crossref","first-page":"23","DOI":"10.4103\/2153-3539.97788","volume":"3","author":"Buckley Julliette M.","year":"2012","journal-title":"Journal of pathology informatics"},{"year":"2015","author":"Ganin Yaroslav","journal-title":"Journal of Machine Learning Research.","key":"p_16"},{"key":"p_28","first-page":"955","volume":"11","author":"Mann Gideon S.","year":"2010","journal-title":"Journal of machine learning research"},{"year":"2015","author":"Marshall Iain J.","journal-title":"Journal of the American Medical Informatics Association.","key":"p_29"},{"issue":"10","key":"p_31","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"Pan Sinno Jialin","year":"2010","journal-title":"IEEE Transactions on Knowledge and Data Engineering"}],"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_00077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:17Z","timestamp":1615585097000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":5,"alternative-id":["10.1162\/tacl_a_00077"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00077","relation":{},"ISSN":["2307-387X"],"issn-type":[{"type":"electronic","value":"2307-387X"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}