HAL : hal-00702445, version 1

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

AAAI 2011 Workshop On Analyzing Microtext, États-Unis (2011)

#hardtoparse: POS Tagging and Parsing the Twitterverse

Jennifer Foster 1, Özlem Çetinoglu 1, Joachim Wagner 1, Joseph Le Roux 2, Stephen Hogan 1, Joakim Nivre 3, Deirdre Hogan 1, Josef Van Genabith 1

(2011)

We evaluate the statistical dependency parser, Malt, on a new dataset of sentences taken from tweets. We use a version of Malt which is trained on gold standard phrase structure Wall Street Journal (WSJ) trees converted to Stanford labelled dependencies. We observe a drastic drop in performance moving from our in-domain WSJ test set to the new Twitter dataset, much of which has to do with the propagation of part-of-speech tagging er- rors. Retraining Malt on dependency trees produced by a state-of-the-art phrase structure parser, which has itself been self-trained on web material, results in a sig- nificant improvement. We analyse this improvement by examining in detail the effect of the retraining on indi- vidual dependency types.

1 :	National Centre for Language Technology (NCLT)
	Dublin City University
2 :	Laboratoire d'informatique Fondamentale de Marseille (LIF)
	CNRS : UMR6166 – Université de la Méditerranée - Aix-Marseille II – Université de Provence - Aix-Marseille I
3 :	Uppsala University
	Uppsala University

Domaine

:

Informatique/Informatique et langage

hal-00702445, version 1

http://hal.archives-ouvertes.fr/hal-00702445

oai:hal.archives-ouvertes.fr:hal-00702445

Contributeur : Joseph Le Roux <>

Soumis le : Mercredi 30 Mai 2012, 11:45:09

Dernière modification le : Vendredi 29 Juin 2012, 16:11:30