Dependency-based syntactic-semantic analysis with PropBank and NomBank
Författare
Summary, in English
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.
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.
Publiceringsår
2008
Språk
Engelska
Sidor
183-187
Publikation/Tidskrift/Serie
Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL)
Länkar
Dokumenttyp
Konferensbidrag
Förlag
Association for Computational Linguistics
Ämne
- Computer Science
Nyckelord
- semantic analysis
- dependency parsing
- Natural language processing
Conference name
Conference on Computational Natural Language Learning (CoNLL)
Conference date
2008-08-16 - 2008-08-17
Status
Published