View Item 

Show simple item record

Getting answers to natural language questions on the Web
dc.contributor.authorRadev, Dragomir R.en_US
dc.contributor.authorLibner, Kelseyen_US
dc.contributor.authorFan, Weiguoen_US
dc.date.accessioned2006-04-19T14:21:42Z
dc.date.available2006-04-19T14:21:42Z
dc.date.issued2002en_US
dc.identifier.citationRadev, Dragomir R.; Libner, Kelsey; Fan, Weiguo (2002)."Getting answers to natural language questions on the Web." Journal of the American Society for Information Science and Technology 53(5): 359-364. <http://hdl.handle.net/2027.42/35290>en_US
dc.identifier.issn1532-2882en_US
dc.identifier.issn1532-2890en_US
dc.identifier.urihttps://hdl.handle.net/2027.42/35290
dc.description.abstractMost popular search engines are not designed for answering natural language questions. However, when we asked hundreds of natural language questions of nine leading search engines, all retrieved at least one correct answer on more than three-quarters of the questions. We identified the best-performing search engines overall for factual natural language questions. We found performance differences depending on the domain of factual question asked. Other aspects of questions also predicted significantly different performance: the number of words in the question, the presence of a proper noun, and whether the question is time dependent. An additional analysis tested for differential performance by specific search engines on these four question factors. The analysis found no evidence for such interactions.en_US
dc.format.extent330785 bytes
dc.format.extent3118 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypetext/plain
dc.language.isoen_US
dc.publisherWiley Subscription Services, Inc., A Wiley Companyen_US
dc.subject.otherComputer Scienceen_US
dc.titleGetting answers to natural language questions on the Weben_US
dc.typeArticleen_US
dc.rights.robotsIndexNoFollowen_US
dc.subject.hlbsecondlevelInformation and Library Scienceen_US
dc.subject.hlbtoplevelSocial Sciencesen_US
dc.description.peerreviewedPeer Revieweden_US
dc.contributor.affiliationumSchool of Information and Department of EECS, University of Michigan, 553 East University Avenue, Ann Arbor, MI 48109en_US
dc.contributor.affiliationumSchool of Information, University of Michigan, 553 East University Avenue, Ann Arbor, MI 48109en_US
dc.contributor.affiliationumSchool of Business, University of Michigan, 553 East University Avenue, Ann Arbor, MI 48109en_US
dc.description.bitstreamurlhttp://deepblue.lib.umich.edu/bitstream/2027.42/35290/1/10053_ftp.pdfen_US
dc.identifier.doihttp://dx.doi.org/10.1002/asi.10053en_US
dc.identifier.sourceJournal of the American Society for Information Science and Technologyen_US
dc.owningcollnameInterdisciplinary and Peer-Reviewed


Files in this item

Name:
10053_ftp.pdf
Size:
323.0KB
Format:
PDF
View/Open

Show simple item record

Remediation of Harmful Language

The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.

Accessibility

If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.