Concordance

Query a 631 >
Shuffle 631 (29,418.6 per million)

	use a <term> block unigram model </term> and	a	<term> word-based trigram language model </term>	#3438 During decoding, we use a block unigram model and a word-based trigram language model.
	<term> bilingual resource </term> required is	a	<term> sentence-aligned parallel corpus </term>	#9800 The only bilingual resource required is a sentence-aligned parallel corpus.
	and generation modules </term> mediated by	a	<term> language neutral meaning representation	#429 The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame.
	<term> hand-crafted system </term> . We describe	a	set of <term> supervised machine learning	#2126 We describe a set of supervised machine learning experiments centering on the construction of statistical models of WH-questions.
	</term><term> accuracy </term> . We describe	a	<term> generative probabilistic model of	#18895 We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity.
	virtue of the fact that both a left and	a	right context were found , <term> heuristics	#15619 At that point, by virtue of the fact that both a left and a right context were found, heuristics can be introduced that predict the nature of the missing fragments.
	results of this experiment , along with	a	preliminary analysis of the factors involved	#763 The results of this experiment, along with a preliminary analysis of the factors involved in the decision making process will be presented here.
tech,13-1-P05-3025,bq	directing the process </term> of <term> translating	a	sentence </term> . The <term> method </term>	#9845 This paper describes a method of interactively visualizing and directing the process of translating a sentence.
	feature vector </term> quality . Finally ,	a	novel <term> feature weighting and selection	#5358 Finally, a novel feature weighting and selection function is presented, which yields superior feature vectors and better word similarity performance.
	</term> that a <term> listener </term> makes when	a	<term> verb </term> is used in a <term> sentence	#11889 These subpredicates may be thought of as the almost inevitable inferences that a listener makes when a verb is used in a sentence.
	ATIS benchmark tests </term> . We describe	a	variation on the <term> standard evaluation	#18853 We describe a variation on the standard evaluation metric which provides a more tightly controlled measure of progress.
	machine learning techniques </term> to build	a	<term> comma checker </term> to be integrated	#11214 In this paper, we describe the research using machine learning techniques to build a comma checker to be integrated in a grammar checker for Basque.
	inference rules </term> can be constructed in	a	<term> semantic network </term> using a variant	#12136 Node-based inference rules can be constructed in a semantic network using a variant of a predicate calculus notation.
	information retrieval techniques </term> use	a	<term> histogram </term> of <term> keywords </term>	#60 Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance.
tech,2-1-H92-1036,bq	reduction in error . We discuss <term> maximum	a	posteriori estimation </term> of <term> continuous	#19055 We discuss maximum a posteriori estimation of continuous density hidden Markov models (CDHMM).
	features </term> . The best system obtains	a	18.6 % improvement over the <term> baseline	#9640 The best system obtains a 18.6% improvement over the baseline on a standard Arabic-English translation task.
	align <term> bilingual texts </term> becomes	a	crucial issue recently . Rather than using	#20537 To align bilingual texts becomes a crucial issue recently.
	metaphors </term> based on the existence of	a	small number of <term> generalized metaphor	#12468 This paper discusses a method of analyzing metaphors based on the existence of a small number of generalized metaphor mappings.
	</term> for <term> expressions </term> including	a	frequent <term> word </term> on <term> APs </term>	#20313 Our study has concluded that we only need to implement the ER for expressions including a frequent word on APs.
	The <term> JAVELIN system </term> integrates	a	flexible , <term> planning-based architecture	#3639 The JAVELIN system integrates a flexible, planning-based architecture with a variety of language processing modules to provide an open-domain question answering capability on free text.


	in Help