Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages

Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages

Show other versions (1)

Title: Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Author: Miloš Stanojević Department: Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Prague, Czech Republic Supervisor: RNDr. Ondřej Bojar Ph....

Full description

Bibliographic Details
Main Author: Stanojevic, Milos
Other Authors: Bojar, Ondřej
Format: Dissertation
Language:English
Published: 2012
Online Access:http://www.nusl.cz/ntk/nusl-305131
id ndltd-nusl.cz-oai-invenio.nusl.cz-305131
record_format oai_dc
spelling ndltd-nusl.cz-oai-invenio.nusl.cz-3051312017-06-28T04:15:54Z Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Stanojevic, Milos Bojar, Ondřej Žabokrtský, Zdeněk Title: Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Author: Miloš Stanojević Department: Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Prague, Czech Republic Supervisor: RNDr. Ondřej Bojar Ph.D. Abstract: We present the theoretical foundations for large-scale discriminative training and their application on the machine translation into MRL languages. The research is concentrated mostly on the two aspects of large-scale discriminative training. The first aspect is the effect of sparse features on the choice of word form and word order. The second aspect is application of different sentence-level metrics as an objective function in the parameter optimization. 2012 info:eu-repo/semantics/masterThesis http://www.nusl.cz/ntk/nusl-305131 eng info:eu-repo/semantics/restrictedAccess
collection NDLTD
language English
format Dissertation
sources NDLTD
description Title: Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Author: Miloš Stanojević Department: Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Prague, Czech Republic Supervisor: RNDr. Ondřej Bojar Ph.D. Abstract: We present the theoretical foundations for large-scale discriminative training and their application on the machine translation into MRL languages. The research is concentrated mostly on the two aspects of large-scale discriminative training. The first aspect is the effect of sparse features on the choice of word form and word order. The second aspect is application of different sentence-level metrics as an objective function in the parameter optimization.
author2 Bojar, Ondřej
author_facet Bojar, Ondřej
Stanojevic, Milos
author Stanojevic, Milos
spellingShingle Stanojevic, Milos
Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
author_sort Stanojevic, Milos
title Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
title_short Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
title_full Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
title_fullStr Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
title_full_unstemmed Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages
title_sort large-scale discriminative training for machine translation into morphologically-rich languages
publishDate 2012
url http://www.nusl.cz/ntk/nusl-305131
work_keys_str_mv AT stanojevicmilos largescalediscriminativetrainingformachinetranslationintomorphologicallyrichlanguages
_version_ 1718473076441612288

Similar Items