UNIGE document Chapitre d'actes
previous document  unige:4699  next document
add to browser collection
Title

Adaptive String Distance Measures for Bilingual Dialect Lexicon Induction

Author
Published in Proceedings of the ACL 2007 Student Research Workshop. Prague - 2007 - . 2007, p. 55-60
Abstract This paper compares different measures of graphemic similarity applied to the task of bilingual lexicon induction between a Swiss German dialect and Standard German. The measures have been adapted to this particular language pair by training stochastic transducers with the Expectation-Maximisation algorithm or by using hand-made transduction rules. These adaptive metrics show up to 11% F-measure improvement over a static metric like Levenshtein distance.
Full text
Proceedings chapter (106 Kb) - public document Free access
Structures
Research group Laboratoire d'Analyse et de Traitement du Langage (LATL)
Citation
(ISO format)
SCHERRER, Yves. Adaptive String Distance Measures for Bilingual Dialect Lexicon Induction. In: Proceedings of the ACL 2007 Student Research Workshop. Prague. [s.l.] : [s.n.], 2007. p. 55-60. https://archive-ouverte.unige.ch/unige:4699

195 hits

154 downloads

Update

Deposited on : 2009-12-23

Export document
Format :
Citation style :