{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T23:00:39Z","timestamp":1767999639726,"version":"3.49.0"},"reference-count":1,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2017,12]]},"abstract":"<jats:p> Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier\u2014i.e., parsers which are more accurate for a given runtime. <\/jats:p>","DOI":"10.1162\/tacl_a_00060","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T15:42:50Z","timestamp":1546011770000},"page":"263-278","source":"Crossref","is-referenced-by-count":7,"title":["Learning to Prune: Exploring the Frontier of Fast and Accurate                     Parsing"],"prefix":"10.1162","volume":"5","author":[{"given":"Tim","family":"Vieira","sequence":"first","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University,"}]},{"given":"Jason","family":"Eisner","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University,"}]}],"member":"281","reference":[{"key":"p_3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00157"}],"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_00060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:11Z","timestamp":1615585091000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43399"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":1,"alternative-id":["10.1162\/tacl_a_00060"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00060","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}