Dependency-based semantic interpretation for answer extraction

Diego Mollá; Ben Hutchinson

Dependency-based semantic interpretation for answer extraction

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

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 language	English
Title of host publication	Proceedings of the 2002 Australasian Natural Language Processing Workshop
Place of Publication	Sydney
Publisher	Macquarie University
Pages	25-32
Number of pages	8
Publication status	Published - 2002
Event	Australasian Natural Language Processing Workshop (2002) - Canberra, ACT Duration: 2 Dec 2002 → 2 Dec 2002

Workshop

Workshop	Australasian Natural Language Processing Workshop (2002)
City	Canberra, ACT
Period	2/12/02 → 2/12/02

Cite this

@inproceedings{5dbd2e5f6175455cbfda1ca6e14e7b63,

title = "Dependency-based semantic interpretation for answer extraction",

abstract = "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.",

author = "Diego Moll{\'a} and Ben Hutchinson",

year = "2002",

language = "English",

pages = "25--32",

booktitle = "Proceedings of the 2002 Australasian Natural Language Processing Workshop",

publisher = "Macquarie University",

note = "Australasian Natural Language Processing Workshop (2002) ; Conference date: 02-12-2002 Through 02-12-2002",

}

TY - GEN

T1 - Dependency-based semantic interpretation for answer extraction

AU - Mollá, Diego

AU - Hutchinson, Ben

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

M3 - Conference proceeding contribution

SP - 25

EP - 32

BT - Proceedings of the 2002 Australasian Natural Language Processing Workshop

PB - Macquarie University

CY - Sydney

T2 - Australasian Natural Language Processing Workshop (2002)

Y2 - 2 December 2002 through 2 December 2002

ER -

Dependency-based semantic interpretation for answer extraction

Abstract

Workshop

Fingerprint

Cite this