Proceedings of the 31st Annual Meeting on Association for Computational Linguistics - 1993
DOI: 10.3115/981574.981607
|View full text |Cite
|
Sign up to set email alerts
|

An empirical study on thematic knowledge acquisition based on syntactic clues and heuristics

Abstract: Thematic knowledge is a basis of semamic interpretation. In this paper, we propose an acquisition method to acquire thematic knowledge by exploiting syntactic clues from training sentences. The syntactic clues, which may be easily collected by most existing syntactic processors, reduce the hypothesis space of the thematic roles. The ambiguities may be further resolved by the evidences either from a trainer or from a large corpus. A set of heurist-cs based on linguistic constraints is employed to guide the ambi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Year Published

1994
1994
2009
2009

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 23 publications
0
2
0
1
Order By: Relevance
“…Both approaches account for only a handful of prepositions; in contrast, for FrameNet we disambiguate 32 prepositions via individual classifiers and over 100 prepositions via the combined classifier. Liu and Soo (1993) present a heuristic approach for relation disambiguation relying upon syntactic clues as well as occurrence of specific prepositions. They assign roles to constituents of a sentence from corpus data provided that sufficient instances are available.…”
Section: Related Workmentioning
confidence: 99%
“…Both approaches account for only a handful of prepositions; in contrast, for FrameNet we disambiguate 32 prepositions via individual classifiers and over 100 prepositions via the combined classifier. Liu and Soo (1993) present a heuristic approach for relation disambiguation relying upon syntactic clues as well as occurrence of specific prepositions. They assign roles to constituents of a sentence from corpus data provided that sufficient instances are available.…”
Section: Related Workmentioning
confidence: 99%
“…Brent (1993) also discovers subcategorization information; in addition, he attempts to discover verbs in the text automatically. Liu and Soo (1993) describe a method for mining information about thematic roles.…”
Section: The Lexiconmentioning
confidence: 99%
“…Sok fajta hasonló szemantikus szerepet definiáltak. Például Liu és társa (Liu & Soo, 1993) 13 szerepet, míg Rosa és társa (Rosa & Francozo, 1999) 23 szerepet definiált.…”
Section: A Domén Független Szemantikus Szerepekunclassified