Concordance

Query using 65 >
Sort Left 65 (3,030.4 per million)

segments of actual tape-recorded descriptions ,	using	<term> organizational and discourse strategies	#15485 The model is embodied in a program, APT, that can reproduce segments of actual tape-recorded descriptions, using organizational and discourse strategies derived through analysis of our corpus.
sense disambiguation performance </term> ,	using	standard <term> WSD evaluation methodology	#7814 We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly on word sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task.
improve upon this initial <term> ranking </term> ,	using	additional <term> features </term> of the <term>	#8701 A second model then attempts to improve upon this initial ranking, using additional features of the tree as evidence.
our best condition for this test suite ,	using	109 <term> training speakers </term> . Second	#17114 This performance is comparable to our best condition for this test suite, using 109 training speakers.
a <term> token classification task </term> ,	using	various <term> tagging strategies </term> to	#10813 There are several approaches that model information extraction as a token classification task, using various tagging strategies to combine multiple tokens.
for <term> speaker adaptation ( SA ) </term>	using	the new <term> SI corpus </term> and a small	#17132 Second, we show a significant improvement for speaker adaptation (SA)using the new SI corpus and a small amount of speech from the new (target) speaker.
surprisingly close to what can be achieved	using	conventional <term> word-trigram recognition	#2247 The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription.
for <term> Japanese sentence analyses </term>	using	an <term> argumentation system </term> by Konolige	#16579 This paper proposes that sentence analysis should be treated as defeasible reasoning, and presents such a treatment for Japanese sentence analysesusing an argumentation system by Konolige, which is a formalization of defeasible reasoning, that includes arguments and defeat rules that capture defeasibility.
<term> Communicator </term> participants are	using	. In this presentation , we describe the	#251 To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using.
describe the methods and hardware that we are	using	to produce a real-time demonstration of	#16874 We describe the methods and hardware that we are using to produce a real-time demonstration of an integrated Spoken Language System.
proprietary <term> Arabic stemmer </term> built	using	<term> rules </term> , <term> affix lists </term>	#4551 Our resource-frugal approach results in 87.5% agreement with a state of the art, proprietary Arabic stemmer built using rules, affix lists, and human annotated text, in addition to an unsupervised component.
the sum of each <term> character </term> . By	using	commands or <term> rules </term> which are	#12312 By using commands or rules which are defined to facilitate the construction of format expected or some mathematical expressions, elaborate and pretty documents can be successfully obtained.
</term> and <term> linguistic pattern </term> . By	using	them , we can automatically extract such	#11442 By using them, we can automatically extract such sentences that express opinion.
</term> is raised from 46.0 % to 60.62 % by	using	this novel approach . <term> Graph unification	#17941 The accuracy rate of syntactic disambiguation is raised from 46.0% to 60.62% by using this novel approach.
in the search space </term> is achieved by	using	<term> semantic </term> rather than <term> syntactic	#17713 A further reduction in the search space is achieved by using semantic rather than syntactic categories on the terminal and non-terminal edges, thereby reducing the amount of ambiguity and thus the number of edges, since only edges with a valid semantic interpretation are ever introduced.
performance gains from the <term> data </term> by	using	<term> class-dependent interpolation </term>	#3073 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> which is parsed very efficiently by	using	the <term> parse record </term> of the first	#18204 The unidentified portion is resolved by re-utterance of that portion which is parsed very efficiently by using the parse record of the first utterance.
sense per collocation observation </term> by	using	triplets of <term> words </term> instead of	#10158 This approach differs from other approaches to WSI in that it enhances the effect of the one sense per collocation observation by using triplets of words instead of pairs.
<term> word string </term> has been obtained by	using	a different <term> LM </term> . Actually ,	#1110 The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM.
Sentence ambiguities </term> can be resolved by	using	domain targeted preference knowledge without	#16325 Sentence ambiguities can be resolved by using domain targeted preference knowledge without using complicated large knowledgebases.


	in Help