{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:57:42Z","timestamp":1760597862479},"reference-count":6,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2017,12]]},"abstract":"<jats:p> Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a sequence of non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the current word is not utilized, which is a relative weakness of shift-reduce parsing. To address this limitation, we leverage a fast neural model to extract lookahead features. In particular, we build a bidirectional LSTM model, which leverages full sentence information to predict the hierarchy of constituents that each word starts and ends. The results are then passed to a strong transition-based constituent parser as lookahead features. The resulting parser gives 1.3% absolute improvement in WSJ and 2.3% in CTB compared to the baseline, giving the highest reported accuracies for fully-supervised parsing. <\/jats:p>","DOI":"10.1162\/tacl_a_00045","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T15:42:50Z","timestamp":1546011770000},"page":"45-58","source":"Crossref","is-referenced-by-count":8,"title":["Shift-Reduce Constituent Parsing with Neural Lookahead                     Features"],"prefix":"10.1162","volume":"5","author":[{"given":"Jiangming","family":"Liu","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design, 8 Somapah Road, Singapore,                         487372,"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, 8 Somapah Road, Singapore,                         487372,"}]}],"member":"281","reference":[{"issue":"2","key":"p_3","first-page":"237","volume":"25","author":"Bangalore Srinivas","year":"1999","journal-title":"Computational Linguistics"},{"key":"p_13","doi-asserted-by":"publisher","DOI":"10.1162\/089120103322753356"},{"key":"p_23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"2","key":"p_30","first-page":"313","volume":"19","author":"Marcus Mitchell P.","year":"1993","journal-title":"Computational Linguistics"},{"issue":"2","key":"p_53","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1017\/S135132490400364X","volume":"11","author":"Xue Naiwen","year":"2005","journal-title":"Natural Language Engineering"},{"key":"p_55","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00037"}],"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_00045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:05Z","timestamp":1615585085000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":6,"alternative-id":["10.1162\/tacl_a_00045"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00045","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}