Concordance

Query how 34 (1,585.2 per million)

documentation . The question is , however ,	how	an interesting information piece would	#42 The question is, however, how an interesting information piece would be found in a large database.
for this purpose . In this paper we show	how	two standard outputs from <term> information	#279 In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser.
standard <term> text browser </term> . We describe	how	this information is used in a <term> prototype	#315 We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function.
context of <term> dialog systems </term> . We show	how	research in <term> generation </term> can be	#997 We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques.
adapted to <term> dialog systems </term> , and	how	the high cost of hand-crafting <term> knowledge-based	#1009 We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques.
<term> speech acts </term> and the decision of	how	to combine them into one or more <term> sentences	#1325 Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences.
</term> are limited . In this paper , we show	how	<term> training data </term> can be supplemented	#3034 In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.
</term> . The demonstration will focus on	how	<term> JAVELIN </term> processes <term> questions	#3667 The demonstration will focus on how JAVELIN processes questions and retrieves the most likely answer candidates from the given text corpus.
probabilities </term> is unstable . Finally , we show	how	this new <term> tagger </term> achieves state-of-the-art	#5599 Finally, we show how this new tagger achieves state-of-the-art results in a supervised, non-training intensive framework.
</term> in <term> English </term> . We demonstrate	how	errors in the <term> machine translations	#7222 We demonstrate how errors in the machine translations of the input Arabic documents can be corrected by identifying and generating from such redundancy, focusing on noun phrases.
results are presented , that demonstrate	how	the proposed <term> method </term> allows to	#7421 Experimental results are presented, that demonstrate how the proposed method allows to better generalize from the training data.
translation systems </term> , and demonstrate	how	our application can be used by <term> developers	#7662 We incorporate this analysis into a diagnostic tool intended for developers of machine translation systems, and demonstrate how our application can be used by developers to explore patterns in machine translation output.
<term> features </term> , without concerns about	how	these <term> features </term> interact or overlap	#8734 The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account.
array-based data structure </term> . We show	how	<term> sampling </term> can be used to reduce	#9180 We show how sampling can be used to reduce the retrieval time by orders of magnitude with no loss in translation quality.
statistical machine translation </term> , we show	how	<term> paraphrases </term> in one <term> language	#9698 Using alignment techniques from phrase-based statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot.
translation probabilities </term> , and show	how	it can be refined to take <term> contextual	#9739 We define a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account.
classifiers </term> . First , we investigate	how	well the <term> addressee </term> of a <term>	#10257 First, we investigate how well the addressee of a dialogue act can be predicted based on gaze, utterance and conversational context features.
time </term> . Furthermore , we will show	how	some <term> evaluation measures </term> can	#10390 Furthermore, we will show how some evaluation measures can be improved by the introduction of word-dependent substitution costs.
that <term> users </term> need by analyzing	how	a <term> user </term> interacts with a system	#11680 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> , the <term> theory </term> specifies	how	different information in <term> memory </term>	#11951 Unlike logic, the theory specifies how different information in memory affects the certainty of the conclusions drawn.


	in Help