Классовые модели
Related Papers
New Models for Improving Supertag Disambiguation
In previous work, supertag disambigua- tion has been presented as a robust, par- tial parsing technique. In this paper we present two approaches: contextual models, which exploit a variety of …...
Evaluating and Combining Approaches to Selectional Preference Acquisition
Previous work on the induction of se- lectional preferences has been mainly carried out for English and has concen- trated almost exclusively on verbs and their direct objects. In this …...
Exploitation d’une marge de tolérance de classification pour améliorer l’apprentissage de modèles acoustiques de classes en reconnaissance de la parole (Exploitation of a classification tolerance margin for improving the estimation of class-based acoustic models for speech recognition) [in French]
_________________________________________________________________________________________________________ Exploitation of a classification tolerance margin for improving the estimation of class-based acoustic models for speech recognition This paper presents the...
QCRI’s Machine Translation Systems for IWSLT’16
AbstractThis paper describes QCRI’s machine translation systems for the IWSLT 2016 evaluation campaign. We participated in the Arabic→English and English→Arabic tracks. We built both Phrase-based and Neural machine translation models, …...