translation output </term> . Subjects were given a set of up to six extracts of <term> translated
</term> . <term> Sentence planning </term> is a set of inter-related but distinct tasks , one
hand-crafted system </term> . We describe a set of <term> supervised machine learning </term>
<term> ONTOSCORE </term> , a system for scoring sets of <term> concepts </term> on the basis of
translation </term> that uses a much simpler set of <term> model parameters </term> than similar
</term> . It is based on : ( 1 ) an extended set of <term> features </term> ; and ( 2 ) <term>
non-NP-antecedents </term> . We present a set of <term> features </term> designed for <term>
is more comprehensive . Specifically , we set up three dimensions of <term> user models
</term> in <term> dialogue </term> . We extract a set of <term> heuristic principles </term> from
</term> of such <term> clauses </term> to create a set of <term> domain independent features </term>
<term> distributional hypothesis </term> in a set of coherent <term> corpora </term> . This paper
</term> , a <term> topic signature </term> is a set of <term> words </term> that tend to co-occur
able , after attending this workshop , to set out building an <term> SMT system </term> themselves
automatically generates <term> paraphrase </term> sets from <term> seed sentences </term> to be used
lr,16-1-I05-5008,bq sentences </term> to be used as <term> reference sets </term> in objective <term> machine translation
lexical and syntactical variation </term> in a set of <term> paraphrases </term> : slightly superior
lr,72-2-I05-5008,bq slightly superior to that of <term> hand-produced sets </term> . The <term> paraphrase </term> sets
sets </term> . The <term> paraphrase </term> sets produced by this <term> method </term> thus
lr,11-3-I05-5008,bq </term> thus seem adequate as <term> reference sets </term> to be used for <term> MT evaluation
</term> . The base <term> parser </term> produces a set of <term> candidate parses </term> for each
hide detail