Concordance

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

uses a <term> trigram language model </term>	to	determine the most probable <term> morpheme	#4677 The algorithm uses a trigram language modelto determine the most probable morpheme sequence for a given input.
in a <term> prototype system </term> designed	to	support <term> information workers </term>	#325 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.
( QA ) systems </term> are very sensitive	to	variations in the phrasing of an <term> information	#10739 State-of-the-art Question Answering (QA) systems are very sensitive to variations in the phrasing of an information need.
task in building the <term> editor </term> was	to	define a set of <term> coherence rules </term>	#17302 Our most important task in building the editor was to define a set of coherence rules that could be computationally applied to ensure the validity of lexical entries.
</term> of <term> human language learners </term> ,	to	the <term> output </term> of <term> machine translation	#570 The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems.
relations </term> among them . The key is	to	identify groups of <term> objects </term> that	#5674 The key is to identify groups of objects that are naturally recognized by humans.
technology </term> development initiative	to	advance the state of the art in <term> CSR	#19543 The CSR (Connected Speech Recognition) corpus represents a new DARPA speech recognition technology development initiative to advance the state of the art in CSR.
HDAGs </term> . We applied the proposed method	to	<term> question classification </term> and <term>	#3844 We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function.
using various <term> tagging strategies </term>	to	combine multiple <term> tokens </term> . We	#10817 There are several approaches that model information extraction as a token classification task, using various tagging strategiesto combine multiple tokens.
This paper reports on two contributions	to	<term> large vocabulary continuous speech	#16981 This paper reports on two contributions to large vocabulary continuous speech recognition.
view that despite recent speculative claims	to	the contrary , current <term> SMT models </term>	#7955 This tends to support the view that despite recent speculative claims to the contrary, current SMT models do have limitations in comparison with dedicated WSD models, and that SMT should benefit from the better predictions made by the WSD models.
<term> summarization </term> has been shown	to	work in <term> documents </term> of certain	#6213 While sentence extraction as an approach to summarization has been shown to work in documents of certain genres, because of the conversational nature of email communication where utterances are made in relation to one made previously, sentence extraction may not capture the necessary segments of dialogue that would make a summary coherent.
<term> FERRET </term> utilizes a novel approach	to	<term> Q/A </term> known as <term> predictive	#11659 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.
set </term> , these modifications combined	to	reduce the <term> speech recognition word	#18750 Together with the use of a larger training set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set.
displays </term> offers techniques superior	to	those of humans for these aspects , while	#12627 This paper defends that view, but claims that direct imitation of human performance is not the best way to implement many of these non-literal aspects of communication; that the new technology of powerful personal computers with integral graphics displays offers techniques superior to those of humans for these aspects, while still satisfying human communication needs.
utilizes <term> typed feature structures </term>	to	control the <term> top-down derivation </term>	#16236 The system utilizes typed feature structuresto control the top-down derivation in a declarative way.
templates </term> - can be used to enhance access	to	<term> text collections </term> via a standard	#304 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.
respects : as a device to represent and	to	use different <term> dialog schemata </term>	#12377 as a device to represent and to use different dialog schemata proposed in empirical conversation analysis;
</term> of about 110,000 <term> words </term> .	To	improve the <term> segmentation </term><term>	#4706 The language model is initially estimated from a small manually segmented corpus of about 110,000 words. To improve the segmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus.
closes with a description of an approach	to	<term> reasoning with dispositions </term>	#13669 The paper closes with a description of an approach to reasoning with dispositions which is based on the concept of a fuzzy syllogism.


	in Help