{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:47:17Z","timestamp":1777639637318,"version":"3.51.4"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,8]]},"abstract":"<jats:p>Seq2seq models based on Recurrent Neural Networks\n\n(RNNs) have recently received a lot of attention\n\nin the domain of Semantic Parsing. While\n\nin principle they can be trained directly on pairs\n\n(natural language utterances, logical forms), their\n\nperformance is limited by the amount of available\n\ndata. To alleviate this problem, we propose to\n\nexploit various sources of prior knowledge: the\n\nwell-formedness of the logical forms is modeled\n\nby a weighted context-free grammar; the likelihood\n\nthat certain entities present in the input utterance\n\nare also present in the logical form is modeled by\n\nweighted finite-state automata. The grammar and\n\nautomata are combined together through an efficient\n\nintersection algorithm to form a soft guide\n\n(\u201cbackground\u201d) to the RNN.We test our method on\n\nan extension of the Overnight dataset and show that\n\nit not only strongly improves over an RNN baseline,\n\nbut also outperforms non-RNN models based\n\non rich sets of hand-crafted features.<\/jats:p>","DOI":"10.24963\/ijcai.2017\/585","type":"proceedings-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T09:14:07Z","timestamp":1501233247000},"page":"4186-4192","source":"Crossref","is-referenced-by-count":5,"title":["Symbolic Priors for RNN-based Semantic Parsing"],"prefix":"10.24963","author":[{"given":"Chunyang","family":"Xiao","sequence":"first","affiliation":[{"name":"Xerox Research Center Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Dymetman","sequence":"additional","affiliation":[{"name":"Xerox Research Center Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claire","family":"Gardent","sequence":"additional","affiliation":[{"name":"CNRS, Loria, UMR 7503"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Twenty-Sixth International Joint Conference on Artificial Intelligence","theme":"Artificial Intelligence","location":"Melbourne, Australia","acronym":"IJCAI-2017","number":"26","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)","University of Technology Sydney (UTS)","Australian Computer Society (ACS)"],"start":{"date-parts":[[2017,8,19]]},"end":{"date-parts":[[2017,8,26]]}},"container-title":["Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T11:54:38Z","timestamp":1501242878000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2017\/585"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2017,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2017\/585","relation":{},"subject":[],"published":{"date-parts":[[2017,8]]}}}