{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T02:24:09Z","timestamp":1778898249650,"version":"3.51.4"},"reference-count":0,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2002,2,15]],"date-time":"2002-02-15T00:00:00Z","timestamp":1013731200000},"content-version":"unspecified","delay-in-days":76,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2001,12]]},"abstract":"<jats:p>One of the main challenges in question-answering is the potential mismatch between the \nexpressions in questions and the expressions in texts. While humans appear to use inference \nrules such as \u2018X writes Y\u2019 implies \u2018X is the author of Y\u2019 in answering questions, such rules \nare generally unavailable to question-answering systems due to the inherent difficulty in constructing \nthem. In this paper, we present an unsupervised algorithm for discovering inference \nrules from text. Our algorithm is based on an extended version of Harris\u2019 Distributional \nHypothesis, which states that words that occurred in the same contexts tend to be similar. \nInstead of using this hypothesis on words, we apply it to paths in the dependency trees of a \nparsed corpus. Essentially, if two paths tend to link the same set of words, we hypothesize \nthat their meanings are similar. We use examples to show that our system discovers many \ninference rules easily missed by humans.<\/jats:p>","DOI":"10.1017\/s1351324901002765","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T13:49:03Z","timestamp":1027777743000},"page":"343-360","source":"Crossref","is-referenced-by-count":178,"title":["Discovery of inference rules for question-answering"],"prefix":"10.1017","volume":"7","author":[{"given":"DEKANG","family":"LIN","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"PATRICK","family":"PANTEL","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2002,2,15]]},"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324901002765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,7]],"date-time":"2019-05-07T21:32:55Z","timestamp":1557264775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324901002765\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,12]]},"references-count":0,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2001,12]]}},"alternative-id":["S1351324901002765"],"URL":"https:\/\/doi.org\/10.1017\/s1351324901002765","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,12]]}}}