{"type":"ScholarlyArticle","title":"Category Translation: Learning to Understand Information on the Internet","authors":[{"name":"Mike Perkowitz","slug":"mike-perkowitz","given":"Mike","family":"Perkowitz","affiliation":""},{"name":"Oren Etzioni","slug":"oren-etzioni","given":"Oren","family":"Etzioni","affiliation":""}],"abstract":"This paper investigates the problem of automatically learning declarative models of information sources available on the Internet . We report on !LA, a domain-independent program that learns the meaning of external information by explaining it in terms of internal categories. In our experiments, !LA starts with knowledge oflocal faculty members, and is able to learn models of the Internet service whois and of the personnel directories available at Berkeley, Brown, Caltech, Cornell, Rice, Rutgers, and UCI, averaging fewer than 40 queries per information source. !LA's hypothesis language is compositions of first-order predicates, and its bias is compactly encoded as a determination . We analyze !LA 's sample complexity both within the Valiant model, and using a probabilistic model specifically tailored to !LA .","doi":null,"url":"https://ijcai.org/proceedings/1995/121","pdf":"https://ijcai.org/proceedings/1995/0121.pdf","markdown":"https://ijcai.org/proceedings/1995/121.md","bibtex":"https://ijcai.org/proceedings/1995/bibtex/121","volume":{"slug":"1995","title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1995","url":"https://ijcai.org/proceedings/1995/","year":1995,"location":"Montréal, Québec, Canada","dates":"","editors":"Chris S. Mellish","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Knowledge Representation","track":"Knowledge Representation","number":121,"pages":{"first":930,"last":937},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}