statistical machine translation ( MT ) </term> , to understand the <term> model </term> 's strengths
Phrasal Lexicon ( DHPL ) </term> [ Zernik88 ] , to facilitate <term> language acquisition </term>
confines of <term> syntax </term> , for instance , to the task of <term> semantic interpretation
<term> machine translation </term> , that is , to make decisions on the basis of <term> translation
of <term> human language learners </term> , to the <term> output </term> of <term> machine translation
able , after attending this workshop , to set out building an <term> SMT system </term>
noted I walked : to walk : : I laughed : to laugh ) . But <term> computational linguists
laughed is to to laugh , noted I walked : to walk : : I laughed : to laugh ) . But <term>
patterns </term> in a large <term> corpus </term> . To a large extent , these <term> statistics </term>
the <term> accuracy rate </term> directly . To make the proposed algorithm robust , the
their <term> translation equivalents </term> . To help this task we have developed an <term>
detected <term> homophone errors </term> . To align <term> bilingual texts </term> becomes
<term> N-Best sentence hypotheses </term> . To avoid <term> grammar coverage problems </term>
values </term> is <term> NP-complete </term> . To deal with this <term> complexity </term> ,
attribute </term> among <term> objects </term> . To overcome this limitation , this paper proposes
these <term> indices </term> can be obtained . To support engaging human users in robust
</term> of about 110,000 <term> words </term> . To improve the <term> segmentation </term><term>
</term> of the described <term> world </term> . To reconstruct the <term> model </term> , the
Lexical-Functional Grammars ( LFG ) </term> to the domain of <term> sentence condensation
methods ( BLEU , NIST , WER and PER ) </term> to building <term> classifiers </term> to predict
hide detail