lr,12-2-P01-1008,bq identification of paraphrases </term> from a <term> corpus of multiple English translations </term>
lr,44-1-N03-1004,bq for <term> answers </term> in multiple <term> corpora </term> . The <term> answering agents </term>
lr,19-4-N03-1012,bq successfully classifies 73.2 % in a <term> German corpus </term> of 2.284 <term> SRHs </term> as either
lr,13-1-N03-2006,bq </term> based on a small-sized <term> bilingual corpus </term> , we use an out-of-domain <term> bilingual
lr,20-1-N03-2006,bq , we use an out-of-domain <term> bilingual corpus </term> and , in addition , the <term> language
lr,33-1-N03-2006,bq model </term> of an in-domain <term> monolingual corpus </term> . We conducted experiments with an
lr,19-3-N03-2006,bq of using an out-of-domain <term> bilingual corpus </term> and the possibility of using the <term>
lr,10-5-N03-2025,bq Markov Model </term> is trained on a <term> corpus </term> automatically tagged by the first
lr,19-2-N03-4010,bq candidates </term> from the given <term> text corpus </term> . The operation of the <term> system
other,15-1-P03-1009,bq classes </term> from undisambiguated <term> corpus data </term> . We describe a new approach
lr,15-5-P03-1031,bq information </term> obtained from <term> dialogue corpora </term> . Unlike conventional methods that
lr,22-2-P03-1050,bq a small ( 10K sentences ) <term> parallel corpus </term> as its sole <term> training resources
lr,7-2-P03-1051,bq by a small <term> manually segmented Arabic corpus </term> and uses it to bootstrap an <term>
lr,28-2-P03-1051,bq </term> from a large <term> unsegmented Arabic corpus </term> . The <term> algorithm </term> uses a
lr,9-4-P03-1051,bq estimated from a small <term> manually segmented corpus </term> of about 110,000 <term> words </term>
lr,21-5-P03-1051,bq million <term> word </term><term> unsegmented corpus </term> , and re-estimate the <term> model
lr,34-5-P03-1051,bq <term> vocabulary </term> and <term> training corpus </term> . The resulting <term> Arabic word
lr,15-6-P03-1051,bq exact match accuracy </term> on a <term> test corpus </term> containing 28,449 <term> word tokens
lr,25-7-P03-1051,bq can create a small <term> manually segmented corpus </term> of the <term> language </term> of interest
lr,15-2-P03-1058,bq </term> from <term> English-Chinese parallel corpora </term> , which are then used for disambiguating
hide detail