Dependency-based semantic interpretation for answer extraction

Diego Mollá, Ben Hutchinson

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


This paper focuses on the use of two algorithms for the integration of two broad-coverage dependency-based parsing systems into ExtrAns, an answer extraction system that operates over Unix manual pages. In the process, ExtrAns uses a semantic interpreter that converts the output of the parser into flat logical forms. The semantic interpreter for the first parsing system, Link Grammar, uses a topdown algorithm, whereas the semantic interpreter for the second parsing system, Conexor FDG, uses a bottom-up algorithm. After showing the differences between the structures returned by both parsing systems, the paper compares the algorithms for semantic interpretation and comments on their adequacy for the production of flat logical forms.
Original languageEnglish
Title of host publicationProceedings of the 2002 Australasian Natural Language Processing Workshop
Place of PublicationSydney
PublisherMacquarie University
Number of pages8
Publication statusPublished - 2002
EventAustralasian Natural Language Processing Workshop (2002) - Canberra, ACT
Duration: 2 Dec 20022 Dec 2002


WorkshopAustralasian Natural Language Processing Workshop (2002)
CityCanberra, ACT


Dive into the research topics of 'Dependency-based semantic interpretation for answer extraction'. Together they form a unique fingerprint.

Cite this