Coupling an annotated corpus and a morphosyntactic lexicon for state-of-the-art POS tagging with less human effort

Pascal Denis 1 Benoît Sagot 1
1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
Inria Paris-Rocquencourt, UPD7 - Université Paris Diderot - Paris 7
Abstract : This paper investigates how to best couple hand-annotated data with information extracted from an external lexical resource to improve POS tagging performance. Focusing on French tagging, we introduce a maximum entropy conditional sequence tagging system that is enriched with information extracted from a morphological resource. This system gives a 97.7% accuracy on the French Treebank, an error reduction of 23% (28% on unknown words) over the same tagger without lexical information. We also conduct experiments on datasets and lexicons of varying sizes in order to assess the best trade-off between annotating data vs. developing a lexicon. We find that the use of a lexicon improves the quality of the tagger at any stage of development of either resource, and that for fixed performance levels the availability of the full lexicon consistently reduces the need for supervised data by at least one half.
Type de document :
Communication dans un congrès
Pacific Asia Conference on Language, Information and Computation, 2009, Hong Kong, China. 2009
Liste complète des métadonnées

https://hal.inria.fr/inria-00514366
Contributeur : Pascal Denis <>
Soumis le : jeudi 2 septembre 2010 - 09:03:19
Dernière modification le : mercredi 12 octobre 2016 - 01:23:22

Identifiants

  • HAL Id : inria-00514366, version 1

Collections

Citation

Pascal Denis, Benoît Sagot. Coupling an annotated corpus and a morphosyntactic lexicon for state-of-the-art POS tagging with less human effort. Pacific Asia Conference on Language, Information and Computation, 2009, Hong Kong, China. 2009. 〈inria-00514366〉

Partager

Métriques

Consultations de la notice

228