A Language-Independent Approach to Extracting Derivational Relations from an Inflectional Lexicon

Abstract : In this paper, we describe and evaluate an unsupervised method for cquiring pairs of lexical entries belonging to the same morphological family, i.e., derivationally related words, starting from a purely inflectional lexicon. Our approach relies on transformation rules that relate lexical entries with the one another, and which are automatically extracted from the inflected lexicon based on surface form analogies and on part-of-speech information. It is generic enough to be applied to any language with a mainly concatenative derivational morphology. Results were obtained and evaluated on English, French, German and Spanish. Precision results are satisfying, and our French results favorably compare with another resource, although its construction relied on manually developed lexicographic information whereas our approach only requires an inflectional lexicon.
Type de document :
Communication dans un congrès
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), May 2014, Reykjavik, Iceland. 2014, 〈http://www.lrec-conf.org/proceedings/lrec2014/pdf/379_Paper.pdf〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01002723
Contributeur : Marion Baranes <>
Soumis le : vendredi 6 juin 2014 - 16:59:08
Dernière modification le : mercredi 12 octobre 2016 - 01:23:50
Document(s) archivé(s) le : samedi 6 septembre 2014 - 12:20:42

Fichier

lrec14_famillemorpho.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01002723, version 1

Collections

Citation

Marion Baranes, Benoît Sagot. A Language-Independent Approach to Extracting Derivational Relations from an Inflectional Lexicon. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), May 2014, Reykjavik, Iceland. 2014, 〈http://www.lrec-conf.org/proceedings/lrec2014/pdf/379_Paper.pdf〉. 〈hal-01002723〉

Partager

Métriques

Consultations de la notice

206

Téléchargements de fichiers

108