Advanced

Dependency-based semantic role labeling of PropBank

Johansson, Richard LU and Nugues, Pierre LU (2008) Empirical Methods in Natural Language Processing In [Host publication title missing] p.69-78
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
dependency parsing, Natural language processing, PropBank, semantic analysis
in
[Host publication title missing]
pages
10 pages
publisher
Association for Computational Linguistics
conference name
Empirical Methods in Natural Language Processing
external identifiers
  • Scopus:78049381722
language
English
LU publication?
yes
id
a491d4f2-25d3-4ed7-b04b-3a06742f77a7 (old id 1229581)
alternative location
http://www.aclweb.org/anthology-new/D/D08/D08-1008.pdf
date added to LUP
2008-09-08 14:16:00
date last changed
2016-10-30 04:38:15
@misc{a491d4f2-25d3-4ed7-b04b-3a06742f77a7,
  abstract     = {We present a PropBank semantic role labeling system for English that is integrated with a dependency parser.<br/><br>
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.<br/><br>
<br/><br>
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.},
  author       = {Johansson, Richard and Nugues, Pierre},
  keyword      = {dependency parsing,Natural language processing,PropBank,semantic analysis},
  language     = {eng},
  pages        = {69--78},
  publisher    = {ARRAY(0x8e4be20)},
  series       = {[Host publication title missing]},
  title        = {Dependency-based semantic role labeling of PropBank},
  year         = {2008},
}