{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T19:58:11Z","timestamp":1648583891005},"reference-count":0,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[1996,12,1]],"date-time":"1996-12-01T00:00:00Z","timestamp":849398400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[1996,12]]},"abstract":"<jats:p>There are currently two philosophies for building grammars and\n parsers: \nhand-crafted, wide coverage grammars; and statistically induced grammars\n and parsers. \nAside from the methodological differences in grammar construction, the\n linguistic \nknowledge which is overt in the rules of handcrafted grammars is hidden\n in the \nstatistics derived by probabilistic methods, which means \nthat generalizations are also \nhidden and the full training process must be repeated for each domain.\n Although \nhandcrafted wide coverage grammars are portable, they can be made more\n efficient \nwhen applied to limited domains, if it is recognized \nthat language in limited domains \nis usually well constrained and certain linguistic constructions are more\n frequent \nthan others. We view a domain-independent grammar as a repository of portable \ngrammatical structures whose combinations are to be specialized for a given \ndomain. We use Explanation-Based Learning (EBL) to identify the relevant\n subset of \na handcrafted general purpose grammar (XTAG) needed to parse in a given\n domain \n(ATIS). We exploit the key properties of Lexicalized Tree-Adjoining Grammars\n to \nview parsing in a limited domain as finite state transduction from strings\n to their \ndependency structures.<\/jats:p>","DOI":"10.1017\/s1351324997001642","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T09:30:22Z","timestamp":1027762222000},"page":"367-368","source":"Crossref","is-referenced-by-count":0,"title":["Explanation-based learning and finite state transducers: applications \nto parsing lexicalized tree adjoining grammars"],"prefix":"10.1017","volume":"2","author":[{"given":"B.","family":"SRINIVAS","sequence":"first","affiliation":[]}],"member":"56","published-online":{"date-parts":[[1996,12,1]]},"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324997001642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,12]],"date-time":"2019-05-12T15:47:45Z","timestamp":1557676065000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324997001642\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996,12]]},"references-count":0,"journal-issue":{"issue":"4","published-print":{"date-parts":[[1996,12]]}},"alternative-id":["S1351324997001642"],"URL":"https:\/\/doi.org\/10.1017\/s1351324997001642","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[1996,12]]}}}