Meny

Javascript is not activated in your browser. This website needs javascript activated to work properly.
Du är här

Dependency-based semantic role labeling of PropBank

Författare:
Publiceringsår: 2008
Språk: Engelska
Sidor: 69-78
Dokumenttyp: Konferensbidrag
Förlag: Association for Computational Linguisics

Sammanfattning

We present a PropBank semantic role labeling system for English that is integrated with a dependency parser.
To tackle the problem of joint syntactic-semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic-semantic output is selected from a candidate pool generated by the subsystems.

We evaluate the system on the CoNLL-2005 test sets using segment-based and dependency-based metrics. Using the segment-based CoNLL-2005 metric, our system achieves a near state-of-the-art F1 figure of 79.90 on the WSJ test set, or 80.67 if punctuation is treated consistently. Using a dependency-based metric, the F1 figure of our system is 85.93 on the WSJ test set from CoNLL-2008 and 73.43 on the Brown test set. Our system is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance.

Disputation

Nyckelord

  • Technology and Engineering
  • dependency parsing
  • Natural language processing
  • PropBank
  • semantic analysis

Övriga

Empirical Methods in Natural Language Processing
2008-10-25/2008-10-27
Honolulu, USA
Published
Yes

Box 117, 221 00 LUND
Telefon 046-222 00 00 (växel)
Telefax 046-222 47 20
lu [at] lu [dot] se

Fakturaadress: Box 188, 221 00 LUND
Organisationsnummer: 202100-3211
Om webbplatsen