The results of a practical </term><term> evaluation </term> of this <term> method </term> on a <term> wide coverage English grammar </term> are given .
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> .
The value of this approach is that as the <term> operational semantics </term> of <term> natural language applications </term> improve , even larger improvements are possible .
In this paper We experimentally evaluate a <term> trainable sentence planner </term> for a <term> spoken dialogue system </term> by eliciting <term> subjective human judgments </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> .
In our method , <term> unsupervised training </term> is first used to train a <term> phone n-gram model </term> for a particular <term> domain </term> ; the <term> output </term> of <term> recognition </term> with this <term> model </term> is then passed to a <term> phone-string classifier </term> .
In this paper we present <term> ONTOSCORE </term> , a system for scoring sets of <term> concepts </term> on the basis of an <term> ontology </term> .
In this paper , we introduce a <term> generative probabilistic optical character recognition ( OCR ) model </term> that describes an end-to-end process in the <term> noisy channel framework </term> , progressing from generation of <term> true text </term> through its transformation into the <term> noisy output </term> of an <term> OCR system </term> .
In this paper , we show how <term> training data </term> can be supplemented with <term> text </term> from the <term> web </term> filtered to match the <term> style </term> and/or <term> topic </term> of the target <term> recognition task </term> , but also that it is possible to get bigger performance gains from the <term> data </term> by using <term> class-dependent interpolation </term> of <term> N-grams </term> .
We evaluate the utility of this <term> constraint </term> in two different <term> algorithms </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> .
In this paper , we describe a <term> phrase-based unigram model </term> for <term> statistical machine translation </term> that uses a much simpler set of <term> model parameters </term> than similar <term> phrase-based models </term> .
In this paper , we propose a novel <term> Cooperative Model </term> for <term> natural language understanding </term> in a <term> dialogue system </term> .
We build this based on both <term> Finite State Model ( FSM ) </term> and <term> Statistical Learning Model ( SLM ) </term> .
In this paper we present a novel , customizable <term> IE paradigm </term> that takes advantage of <term> predicate-argument structures </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> .
In this paper we formulate <term> story link detection </term> and <term> new event detection </term> as <term> information retrieval task </term> and hypothesize on the impact of <term> precision </term> and <term> recall </term> on both <term> systems </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> .
hide detail