Natural EUGENE Department Language CHARNIAK of Computer Learning Science, Brown University, Prouzdence, RI (ed@cs,brown.edu) The branch of artificial intelligence dealing with natural language processing (NLP) has undergone a quiet revolution. Ten years ago AI NLP work could be characterized as knowledge-based in its orientation and hand-tooled in its methodology. Because I wish to characterize these as the bad old days, I pick on my own work, but virtually any piece of work from the time would do. Ten years ago I was, among other things, concerned with plan recognition in NLP. To take an example I used at the time, suppose you read Fred wanted got a rope. to kill himself. He You would, of course, infer than Fred was going to hang himself. The question I was irlterested in was how we combine the clues kill and rope to suggest hang. The method I proposed was a deliberately dumb, but fast, scheme whereby marks were passed from the words in the text into a knowledge base and the system would look for intersections. The idea was that kill would connect to hang and the knowledge base would contain the fact that hanging involves
End of preview. The entire article is 3 pages. To view the full-text, please rent this article to continue.
/lp/association-for-computing-machinery/natural-language-learning-M2JzED9TkQ
Welcome to DeepDyve! Rent Premier Research Articles and Save Up to 90%
Natural language learning
Charniak, Eugene
Follow ACM Computing Surveys (CSUR)
, Volume 27 (3)
Association for Computing Machinery – Sep 1, 1995
More Info
More Like This Article
View All dataSource[]=actageo&dataSource[]=aspet&dataSource[]=aaos&dataSource[]=aacc&dataSource[]=aacr&dataSource[]=aea&dataSource[]=aip&dataSource[]=ajnr&dataSource[]=ams&dataSource[]=aps_physical&dataSource[]=appi_book&dataSource[]=appi_journal&dataSource[]=apha&dataSource[]=asip&dataSource[]=asm&dataSource[]=asn&dataSource[]=aspb&dataSource[]=avs&dataSource[]=annual_reviews&dataSource[]=arxiv&dataSource[]=acm&dataSource[]=berghahn&dataSource[]=cabi&dataSource[]=clinical_trials&dataSource[]=dailymed&dataSource[]=degruyter&dataSource[]=du_press&dataSource[]=esa&dataSource[]=eu_press&dataSource[]=elsevier&dataSource[]=emerald&dataSource[]=ejtr&dataSource[]=emea&dataSource[]=epo&dataSource[]=faseb&dataSource[]=gsa&dataSource[]=health_affairs&dataSource[]=hindawi&dataSource[]=imanager&dataSource[]=imedpub&dataSource[]=informa_healthcare&dataSource[]=informs&dataSource[]=iop&dataSource[]=iucr&dataSource[]=iospress&dataSource[]=jbjs&dataSource[]=leftcoast&dataSource[]=lu_press&dataSource[]=mesharpe&dataSource[]=mary_ann_liebert&dataSource[]=medline&dataSource[]=mit_press&dataSource[]=nature&dataSource[]=oxford&dataSource[]=pier_professional&dataSource[]=pnas&dataSource[]=portlandpress&dataSource[]=psyc_articles&dataSource[]=psyc_books&dataSource[]=psyc_critiques&dataSource[]=plos_journal&dataSource[]=pubmed_central&dataSource[]=rsna&dataSource[]=rockefeller&dataSource[]=rcn&dataSource[]=ria&dataSource[]=rsc&dataSource[]=sage&dataSource[]=spie&dataSource[]=springer_journal&dataSource[]=springer&dataSource[]=taylor_francis&dataSource[]=aps&dataSource[]=the_scientist&dataSource[]=uc_press&dataSource[]=uspto_abstract&dataSource[]=wiley&dataSource[]=pct
© 2012 DeepDyve, Inc. All rights reserved.
Terms of Service | Privacy Policy
