The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies

Mihai Surdeanu, Richard Johansson, Adam Meyers, Lluís Màrquez, Joakim Nivre

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

The Conference on Computational Natural
Language Learning is accompanied every
year by a shared task whose purpose
is to promote natural language processing
applications and evaluate them in a standard
setting. In 2008 the shared task was
dedicated to the joint parsing of syntactic
and semantic dependencies. This shared
task not only unifies the shared tasks of
the previous four years under a unique
dependency-based formalism, but also extends
them significantly: this year’s syntactic
dependencies include more information
such as named-entity boundaries; the
semantic dependencies model roles of both
verbal and nominal predicates. In this paper,
we define the shared task and describe
how the data sets were created. Furthermore,
we report and analyze the results and
describe the approaches of the participating
systems.
Original languageEnglish
Title of host publicationProceedings of the 12th Conference on Computational Natural Language Learning (CoNLL)
PublisherAssociation for Computational Linguistics
Pages159-177
Number of pages18
Publication statusPublished - 2008
EventConference on Computational Natural Language Learning (CoNLL) - Manchester
Duration: 2008 Aug 162008 Aug 17

Conference

ConferenceConference on Computational Natural Language Learning (CoNLL)
Period2008/08/162008/08/17

Subject classification (UKÄ)

  • Computer Sciences

Free keywords

  • semantic analysis
  • dependency parsing
  • Natural language processing

Fingerprint

Dive into the research topics of 'The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies'. Together they form a unique fingerprint.

Cite this