AnswerFinder: question answering by combining lexical, syntactic and semantic information

Diego Mollá, Mary Gardiner

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review


We present a question answering system that combines information at the lexical, syntactic, and semantic levels, in the process to find and rank the candidate answer sentences. The candidate exact answers are extracted from the candidate answer sentences by means of a combination of information-extraction techniques (named entity recognition) and patterns based on logical forms. The system participated in the question answering track of TREC 2004.
Original languageEnglish
Title of host publicationProceedings of the Australian Language Technology Workshop 2004
EditorsAsh Asudeh, Cécile Paris, Stephen Wan
Place of PublicationCanberra, ACT
PublisherThe Australian Speech Science and Technology Association (ASSTA)
Number of pages8
ISBN (Print)0958194610
Publication statusPublished - 2004
EventAustralian Language Technology Workshop 2004 - Sydney, Australia
Duration: 8 Dec 20048 Dec 2004


WorkshopAustralian Language Technology Workshop 2004


Dive into the research topics of 'AnswerFinder: question answering by combining lexical, syntactic and semantic information'. Together they form a unique fingerprint.

Cite this