Normal view MARC view ISBD view

Dealing with Data Sparseness in SMT with Factored Models and Morphological Expansion: a Case Study on Croatian / Victor M. Sanchez-Cartagena, Nikola Ljubešić, Filip Klubička.

By: Sanchez-Cartagena, Victor M.
Contributor(s): Ljubešić, Nikola, informatičar [aut] | Klubička, Filip [aut].
Material type: ArticleArticleDescription: 354-360 str.Other title: Dealing with Data Sparseness in SMT with Factored Models and Morphological Expansion: a Case Study on Croatian [Naslov na engleskom:].Subject(s): 5.04 | data sparseness, factored translation models, morphological expansion | data sparseness, factored translation models, morphological expansionOnline resources: Elektronička verzija In: Baltic Journal of Modern Computing 4 (2016), 2 ; str. 354-360Summary: This paper describes our experience using available linguistic resources for Croatian in order to address data sparseness when building an English-to-Croatian general domain phrase- based statistical machine translation system. We report the results obtained with factored translation models and morphological expansion, highlight the impact of the algorithm used for tagging the corpora, and show that the improvement brought by these methods is compatible with the application of data selection on out-of-domain parallel corpora.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

This paper describes our experience using available linguistic resources for Croatian in order to address data sparseness when building an English-to-Croatian general domain phrase- based statistical machine translation system. We report the results obtained with factored translation models and morphological expansion, highlight the impact of the algorithm used for tagging the corpora, and show that the improvement brought by these methods is compatible with the application of data selection on out-of-domain parallel corpora.

Projekt MZOS projekt

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//