2005 · 40 citations · 11 references
ComputingComputer ScienceComputational LinguisticsInformation RetrievalNatural Language ProcessingInformation ExtractionKnowledge ExtractionNamed Entity RecognitionQuestion AnsweringRelation ExtractionRetrieval ModelsDocument RetrievalFactoid Question AnsweringGeneral KnowledgeKnowledge Source IdentificationQuestion Answering SystemsSynonymy
MIT CSAIL's entries for the TREC Question Answering track (Voorhees, 2005) focused on incorporating external general-knowledge sources into the question answering process. We also explored the e#ect of document retrieval on factoid question answering, in cooperation with a community focus on document retrieval. For the new relationship task, we present a new passage-retrieval based algorithm emphasizing synonymy, which performed best among automatic systems this year. Our most prominent new external knowledge source is the Wikipedia, and its most useful component is the synonymy implicit in its subtitles and redirect link structure. Wikipedia is also a large new source of hypernym information. The main task included factoid questions, for which we modified the freely available Web-based Aranea question answering engine; list questions, for which we used hypernym hierarchies to constrain candidate answers; and definitional `other' questions, for which we combined can
11
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
An Algorithm that Learns What's in a Name
Daniel M. Bikel, Richard Schwartz, Ralph Weischedel · Machine Learning · 1999 · 784 citations · Full text
Quantitative evaluation of passage retrieval algorithms for question answering
Stefanie Tellex, Boris Katz, Jimmy Lin et al. · 2003 · 284 citations
Retrieval and novelty detection at the sentence level
James Allan, Courtney Wade, A. O. Bolivar · 2003 · 281 citations
Annotating the world wide web using natural language
Boris Katz · 1997 · 159 citations