• Treffer 5 von 9
Zurück zur Trefferliste

The CoNLL 2007 shared task on dependency parsing

  • The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, we define the tasks of the different tracks and describe how the data sets were created from existing treebanks for ten languages. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results.
Metadaten
Verfasserangaben:Joakim Nivre, Johan Hall, Sandra KüblerORCiDGND, Ryan McDonald, Jens Nilsson, Sebastian Riedel, Deniz Yuret
URN:urn:nbn:de:hebis:30-1111251
URL:http://cl.indiana.edu/~skuebler/papers/sharedtask.pdf
Titel des übergeordneten Werkes (Englisch):Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Verlag:Association for Computational Linguistics
Verlagsort:Stroudsburg, PA
Dokumentart:Teil eines Buches (Kapitel)
Sprache:Englisch
Jahr der Fertigstellung:2007
Jahr der Erstveröffentlichung:2007
Veröffentlichende Institution:Universitätsbibliothek Johann Christian Senckenberg
Datum der Freischaltung:03.11.2008
Seitenzahl:18
Erste Seite:915
Letzte Seite:932
Quelle:http://jones.ling.indiana.edu/~skuebler/papers/sharedtask.pdf ; Proceedings of the CoNLL 2007 Shared Task. Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL 2007) - Prague, Czech
HeBIS-PPN:206930356
Institute:keine Angabe Fachbereich / Extern
DDC-Klassifikation:4 Sprache / 40 Sprache / 400 Sprache
Sammlungen:Linguistik
Linguistik-Klassifikation:Linguistik-Klassifikation: Computerlinguistik / Computational linguistics
Lizenz (Deutsch):License LogoDeutsches Urheberrecht