Coupling an annotated corpus and a lexicon for state-of-the-art POS tagging - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Language Resources and Evaluation Année : 2012

Coupling an annotated corpus and a lexicon for state-of-the-art POS tagging

Résumé

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.
Fichier principal
Vignette du fichier
lre12-denis-sagot.pdf (132.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00614819 , version 1 (20-07-2012)

Identifiants

Citer

Pascal Denis, Benoît Sagot. Coupling an annotated corpus and a lexicon for state-of-the-art POS tagging. Language Resources and Evaluation, 2012, 46 (4), pp.721-736. ⟨10.1007/s10579-012-9193-0⟩. ⟨inria-00614819⟩
409 Consultations
884 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More