Concordance

Query to 432 >
Sort Right 432 >
Shuffle 432 >
Subparts filter 432 (20,140.8 per million)

that greatly reduce the computation needed	to	compute the <term> N-Best sentence hypotheses	#16896 We describe algorithms that greatly reduce the computation needed to compute the N-Best sentence hypotheses.
</term> . The formalism 's intended usage is	to	relate <term> expressions of natural languages	#16488 The formalism's intended usage is to relate expressions of natural languages to their associated semantics represented in a logical form language, or to their translates in another natural language; in summary, we intend it to allow TAGs to be used beyond their role in syntax proper.
system while gathering information related	to	a particular scenario . This paper introduces	#11691 FERRET utilizes a novel approach to Q/A known as predictive questioning which attempts to identify the questions (and answers) that users need by analyzing how a user interacts with a system while gathering information related to a particular scenario.
<term> computational linguists </term> seem	to	be quite dubious about <term> analogies between	#5888 But computational linguists seem to be quite dubious about analogies between sentences: they would not be enough numerous to be of any use.
information into its <term> lexicon </term> according	to	its individual needs . However , some of	#15938 Although every natural language system needs a computational lexicon, each system puts different amounts and types of information into its lexicon according to its individual needs.
natural language </term> , it has been difficult	to	detect <term> error characters </term> which	#20630 In optical character recognition and continuous speech recognition of a natural language, it has been difficult to detect error characters which are wrongly deleted and inserted.
to be both efficient and easily adaptable	to	a variety of applications . The system	#12865 Chat-80 has been designed to be both efficient and easily adaptable to a variety of applications.
important in several respects : as a device	to	represent and to use different <term> dialog	#12374 as a device to represent and to use different dialog schemata proposed in empirical conversation analysis;
propose candidate <term> antecedents </term> and	to	evaluate each other 's proposals . This	#14993 Thus we have implemented a blackboard-like architecture in which individual partial theories can be encoded as separate modules that can interact to propose candidate antecedents and to evaluate each other's proposals.
</term> . As each new <term> edge </term> is added	to	the <term> chart </term> , the algorithm checks	#17606 As each new edge is added to the chart, the algorithm checks only the topmost of the edges adjacent to it, rather than all such edges as in conventional treatments.
</term> is a set of <term> words </term> that tend	to	co-occur with it . <term> Topic signatures	#6924 Given a particular concept, or word sense, a topic signature is a set of words that tend to co-occur with it.
We describe a novel <term> approach </term>	to	<term> statistical machine translation </term>	#9206 We describe a novel approachto statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation.
</term> . This paper describes an extension	to	the <term> MIT ATIS ( Air Travel Information	#19338 This paper describes an extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a full linguistic analysis fails.
and the difference could narrow further	to	6.5 % if we disregard the advantage that	#4897 On a subset of the most difficult SENSEVAL-2 nouns, the accuracy difference between the two approaches is only 14.0%, and the difference could narrow further to 6.5% if we disregard the advantage that manually sense-tagged data have in their sense coverage.
</term> on both sides of a <term> word </term>	to	be tagged , and evaluate it in both the	#5511 We present a new HMM tagger that exploits context on both sides of a wordto be tagged, and evaluate it in both the unsupervised and supervised case.
, <term> communication </term> . Our goal is	to	recognize and isolate such <term> miscommunications	#14501 Our goal is to recognize and isolate such miscommunications and circumvent them.
<term> maximum likelihood criterion </term>	to	train a <term> log-linear block bigram model	#9591 We use a maximum likelihood criterionto train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g. block bigram features.
focusing especially on the changes made	to	the <term> SUMMIT recognizer </term> . These	#18704 This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer.
generate <term> cooperative responses </term>	to	each <term> user </term> in <term> spoken dialogue	#4290 We address appropriate user modeling in order to generate cooperative responsesto each user in spoken dialogue systems.
<term> human listeners </term> are usually able	to	cope with these deviations with little	#12704 Their human listeners are usually able to cope with these deviations with little difficulty.


	in Help