An alternative <term> index </term> could be the activity such as discussing , planning , informing , story-telling , etc . This paper addresses the problem of the <term> automatic detection </term> of those activities in meeting situation and everyday rejoinders .
We believe that these <term> evaluation techniques </term> will provide information about both the <term> human language learning process </term> , the <term> translation process </term> and the <term> development </term> of <term> machine translation systems </term> . This , the first experiment in a series of experiments , looks at the <term> intelligibility </term> of <term> MT output </term> .
We describe our use of this approach in numerous fielded <term> user studies </term> conducted with the U.S. military . This paper proposes a practical approach employing <term> n-gram models </term> and <term> error-correction rules </term> for <term> Thai key prediction </term> and <term> Thai-English language identification </term> .
Our approach yields <term> phrasal and single word lexical paraphrases </term> as well as <term> syntactic paraphrases </term> . This paper presents a <term> formal analysis </term> for a large class of <term> words </term> called <term> alternative markers </term> , which includes <term> other ( than ) </term> , <term> such ( as ) </term> , and <term> besides </term> .
We report on different aspects of the <term> predictive performance </term> of our <term> models </term> , including the influence of various <term> training and testing factors </term> on <term> predictive performance </term> , and examine the relationships among the target variables . This paper describes a method for <term> utterance classification </term> that does not require <term> manual transcription </term> of <term> training data </term> .
A novel <term> bootstrapping approach </term> to <term> Named Entity ( NE ) tagging </term> using <term> concept-based seeds </term> and <term> successive learners </term> is presented . This approach only requires a few <term> common noun </term> or <term> pronoun </term><term> seeds </term> that correspond to the <term> concept </term> for the targeted <term> NE </term> , e.g. he/she/man / woman for <term> PERSON NE </term> .
The experimental results prove our claim that accurate <term> predicate-argument structures </term> enable high quality <term> IE </term> results . This paper proposes the <term> Hierarchical Directed Acyclic Graph ( HDAG ) Kernel </term> for <term> structured natural language data </term> .
Experimental results validate our hypothesis . This paper concerns the <term> discourse understanding process </term> in <term> spoken dialogue systems </term> .
This paper concerns the <term> discourse understanding process </term> in <term> spoken dialogue systems </term> . This process enables the <term> system </term> to understand <term> user utterances </term> based on the <term> context </term> of a <term> dialogue </term> .
By holding multiple <term> candidates </term> for <term> understanding </term> results and resolving the <term> ambiguity </term> as the <term> dialogue </term> progresses , the <term> discourse understanding accuracy </term> can be improved . This paper proposes a method for resolving this <term> ambiguity </term> based on <term> statistical information </term> obtained from <term> dialogue corpora </term> .
Experimental evaluation shows that the <term> cooperative responses </term> adaptive to <term> individual users </term> serve as good guidance for <term> novice users </term> without increasing the <term> dialogue duration </term> for <term> skilled users </term> . This paper presents an <term> unsupervised learning approach </term> to building a <term> non-English ( Arabic ) stemmer </term> .
We also investigate the reason for that difference . This paper presents a <term> machine learning </term> approach to bare <term> sluice disambiguation </term> in <term> dialogue </term> .
We present a <term> text mining method </term> for finding <term> synonymous expressions </term> based on the <term> distributional hypothesis </term> in a set of coherent <term> corpora </term> . This paper proposes a new methodology to improve the <term> accuracy </term> of a <term> term aggregation system </term> using each author 's text as a coherent <term> corpus </term> .
We present <term> Minimum Bayes-Risk ( MBR ) decoding </term> for <term> statistical machine translation </term> . This statistical approach aims to minimize <term> expected loss of translation errors </term> under <term> loss functions </term> that measure <term> translation performance </term> .
We describe a new system that enhances <term> Criterion </term> 's capability , by evaluating multiple aspects of <term> coherence </term> in <term> essays </term> . This system identifies <term> features </term> of <term> sentences </term> based on <term> semantic similarity measures </term> and <term> discourse structure </term> .
We evaluated the <term> topic signatures </term> on a <term> WSD </term> task , where we trained a <term> second-order vector co-occurrence algorithm </term> on standard <term> WSD datasets </term> , with promising results . This paper presents a novel <term> ensemble learning approach </term> to <term> resolving German pronouns </term> .
We demonstrate how errors in the <term> machine translations </term> of the input <term> Arabic documents </term> can be corrected by identifying and generating from such <term> redundancy </term> , focusing on <term> noun phrases </term> . This paper presents a <term> maximum entropy word alignment algorithm </term> for <term> Arabic-English </term> based on <term> supervised training data </term> .
<term> Performance </term> of the <term> algorithm </term> is contrasted with <term> human annotation performance </term> . This paper presents a <term> phrase-based statistical machine translation method </term> , based on <term> non-contiguous phrases </term> , i.e. <term> phrases </term> with gaps .
Experimental results are presented , that demonstrate how the proposed <term> method </term> allows to better generalize from the <term> training data </term> . This paper investigates some <term> computational problems </term> associated with <term> probabilistic translation models </term> that have recently been adopted in the literature on <term> machine translation </term> .
Yet , they are scarcely used for the assessment of <term> language pairs </term> like <term> English-Chinese </term> or <term> English-Japanese </term> , because of the <term> word segmentation problem </term> . This study establishes the equivalence between the standard use of <term> BLEU </term> in <term> word n-grams </term> and its application at the <term> character </term> level .
hide detail