Advanced

Dependency-based syntactic-semantic analysis with PropBank and NomBank

Johansson, Richard LU and Nugues, Pierre LU (2008) Conference on Computational Natural Language Learning (CoNLL) In Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL) p.183-187
Abstract
This paper presents our contribution in the closed track of the 2008 CoNLL Shared Task. To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a bottom-up 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.



The system achieved the top score in the closed challenge: a labeled syntactic accuracy of 89.32%, a labeled semantic F1 of 81.65, and a labeled macro F1 of 85.49.
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
semantic analysis, dependency parsing, Natural language processing
in
Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL)
pages
5 pages
publisher
Association for Computational Linguistics
conference name
Conference on Computational Natural Language Learning (CoNLL)
external identifiers
  • Scopus:84865074632
language
English
LU publication?
yes
id
fa25bce8-dec5-4313-aa20-5a6389923563 (old id 1229589)
alternative location
http://www.cnts.ua.ac.be/conll2008/pdf/18387.pdf
date added to LUP
2008-09-08 14:19:27
date last changed
2016-10-30 04:41:55
@misc{fa25bce8-dec5-4313-aa20-5a6389923563,
  abstract     = {This paper presents our contribution in the closed track of the 2008 CoNLL Shared Task. To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a bottom-up projective parser using pseudo-projective transformations, and the semantic model uses global<br/><br>
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>
The system achieved the top score in the closed challenge: a labeled syntactic accuracy of 89.32%, a labeled semantic F1 of 81.65, and a labeled macro F1 of 85.49.},
  author       = {Johansson, Richard and Nugues, Pierre},
  keyword      = {semantic analysis,dependency parsing,Natural language processing},
  language     = {eng},
  pages        = {183--187},
  publisher    = {ARRAY(0xa3c42c8)},
  series       = {Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL)},
  title        = {Dependency-based syntactic-semantic analysis with PropBank and NomBank},
  year         = {2008},
}