database </term> and detect those automatically which is shown on a large <term> database </term>
mixed-initiative speech dialogue interactions </term> which reach beyond current capabilities in <term>
infrastructure </term> for <term> dialogue systems </term> which all <term> Communicator </term> participants
evaluation </term> of the <term> system </term> , which while broadly positive indicates further
Even more illuminating was the factors on which the <term> assessors </term> made their decisions
were asked to mark the <term> word </term> at which they made this decision . The results of
inter-related but distinct tasks , one of which is <term> sentence scoping </term> , i.e. the
</term> has revealed many attractive properties which may be used in <term> NLP </term> . In particular
</term> are directed by a <term> guide </term> which uses the <term> shared derivation forest </term>
</term> called <term> alternative markers </term> , which includes <term> other ( than ) </term> , <term>
connection to <term> Montague semantics </term> which can be viewed as a <term> formal computation
WH-questions </term> . These <term> models </term> , which are built from <term> shallow linguistic
are employed to predict target variables which represent a <term> user 's informational
multi-source approach to question answering </term> which is based on combining the results from
word-based models </term> . Our empirical results , which hold for all examined <term> language pairs
<term> predicate argument structures </term> , which is central to our <term> IE paradigm </term>
data </term> . We describe a new approach which involves clustering <term> subcategorization
<term> evaluation scheme </term> is proposed which accounts for the effect of <term> polysemy
English-Chinese parallel corpora </term> , which are then used for disambiguating the <term>
that the <term> features </term> in terms of which we formulate our <term> heuristic principles
hide detail