{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T21:02:59Z","timestamp":1791406979926,"version":"4.3.3"},"reference-count":4,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2014,12]]},"abstract":"<jats:p> We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines. <\/jats:p>","DOI":"10.1162\/tacl_a_00197","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T15:43:26Z","timestamp":1546011806000},"page":"477-490","source":"Crossref","is-referenced-by-count":67,"title":["A Joint Model for Entity Analysis: Coreference, Typing, and                     Linking"],"prefix":"10.1162","volume":"2","author":[{"given":"Greg","family":"Durrett","sequence":"first","affiliation":[{"name":"Computer Science Division, University of California, Berkeley,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Klein","sequence":"additional","affiliation":[{"name":"Computer Science Division, University of California, Berkeley,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"p_12","first-page":"2121","volume":"12","author":"Duchi John","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"p_21","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.artint.2012.04.005","volume":"194","author":"Hachey Ben","year":"2013","journal-title":"Artificial Intelligence"},{"key":"p_37","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.artint.2012.03.006","volume":"194","author":"Nothman Joel","year":"2013","journal-title":"Artificial Intelligence"},{"key":"p_52","doi-asserted-by":"publisher","DOI":"10.1162\/089120101753342653"}],"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_00197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:39:00Z","timestamp":1615585140000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":4,"alternative-id":["10.1162\/tacl_a_00197"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00197","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]}}}