Dependency parsing and semantic role labeling as a single task

R. Morante, V. Van Asch, A. Van den Bosch

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

We present a comparison between two systems
for establishing syntactic and semantic dependencies: one that performs dependency parsing
and semantic role labeling as a single task, and
another that performs the two tasks in isolation. The systems are based on local memorybased classifiers predicting syntactic and semantic dependency relations between pairs of words.
In a second global phase, the systems perform
a deterministic ranking procedure in which the
output of the local classifiers is combined per
sentence into a dependency graph and semantic role labeling assignments for all predicates.
The comparison shows that in the learning phase
a joint approach produces better-scoring classifiers, while after the ranking phase the isolated
approach produces the most accurate syntactic
dependencies, while the joint approach yields the
most accurate semantic role assignments.
Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Recent Advances in Natural Language Processing (RANLP-2009)
PublisherAssociation for Computational Linguistics (ACL)
Publication statusPublished - 2009

Fingerprint

Dive into the research topics of 'Dependency parsing and semantic role labeling as a single task'. Together they form a unique fingerprint.

Cite this