|
|
Czech-Slovak Statistical Machine Translation
Astaloš, Lukáš ; Kouřil, Jan (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to design, implement and evaluate the translation system capable of translating texts from Czech to Slovak language. It describes theoretical foundations of statistical machine translation and then the phase of design and development of system. The chosen strategy was to build phrase-based translation model using one large parallel corpus in combination with language model from local institute of linguistics. The statistical machine translation Moses was used to achieve this goal. The vocabulary translation of unknown words using stemming was proposed and tested. Precision of build system was evaluated with BLEU score and it achieved comparable results with other systems.
|
|
|
Parallel Text Alignment
Kadlček, Filip ; Grézl, František (referee) ; Smrž, Pavel (advisor)
This thesis is concerned to align parallel corpus. In the first part of thesis are describe acceses to align and some tool to align. As first describe a statistical align, but the main part is specialize to align with use dictionary, which is the main part of this thesis. In the midle part is introduce the princip of dictionary align and a simple example of align. At the end of work are sumarize obtained results and are noted proposals for future develop.
|
|
|
Parallel Text Alignment
Kadlček, Filip ; Grézl, František (referee) ; Smrž, Pavel (advisor)
This thesis is concerned to align parallel corpus. In the first part of thesis are describe acceses to align and some tool to align. As first describe a statistical align, but the main part is specialize to align with use dictionary, which is the main part of this thesis. In the midle part is introduce the princip of dictionary align and a simple example of align. At the end of work are sumarize obtained results and are noted proposals for future develop.
|
|
|
Czech-Slovak Statistical Machine Translation
Astaloš, Lukáš ; Kouřil, Jan (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to design, implement and evaluate the translation system capable of translating texts from Czech to Slovak language. It describes theoretical foundations of statistical machine translation and then the phase of design and development of system. The chosen strategy was to build phrase-based translation model using one large parallel corpus in combination with language model from local institute of linguistics. The statistical machine translation Moses was used to achieve this goal. The vocabulary translation of unknown words using stemming was proposed and tested. Precision of build system was evaluated with BLEU score and it achieved comparable results with other systems.
|
guest ::
