| </term> from <term> structured data </term> ( | based | on a <term> typing-algorithm </term> and <term> | #1984 Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deduction in a resource sensitive logic, and a learning algorithm from structured data ( based on a typing-algorithm and type-unification). | ||
| to <term> question answering </term> which is | based | on combining the results from different | #2337 Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora. | ||
| implementation of the <term> model </term> | based | on <term> finite-state models </term> , demonstrate | #2752 We present an implementation of the modelbased on finite-state models, demonstrate the model's ability to significantly reduce character and word error rate, and provide evaluation results involving automatic extraction of translation lexicons from printed text. | ||
| translation quality </term> of <term> EBMT </term> | based | on a <term> small-sized bilingual corpus </term> | #3089 In order to boost the translation quality of EBMTbased on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus. | ||
| on <term> block selection criteria </term> | based | on <term> unigram counts </term> and <term> phrase | #3470 We show experimental results on block selection criteriabased on unigram counts and phrase length. | ||
| <term> dialogue system </term> . We build this | based | on both <term> Finite State Model ( FSM ) | #3500 We build this based on both Finite State Model (FSM) and Statistical Learning Model (SLM). | ||
| central to our <term> IE paradigm </term> . It is | based | on : ( 1 ) an extended set of <term> features | #3753 It is based on: (1) an extended set of features; and (2) inductive decision tree learning. | ||
| tech,3-1-P03-1022,ak | data </term> . We apply a <term> decision tree | based | approach </term> to <term> pronoun resolution | #3979 We apply a decision tree based approach to pronoun resolution in spoken dialogue. | |
| to understand <term> user utterances </term> | based | on the <term> context </term> of a <term> dialogue | #4148 This process enables the system to understand user utterancesbased on the context of a dialogue. | ||
| for resolving this <term> ambiguity </term> | based | on <term> statistical information </term> obtained | #4227 This paper proposes a method for resolving this ambiguitybased on statistical information obtained from dialogue corpora. | ||
| </term> . <term> Dialogue strategies </term> | based | on the <term> user modeling </term> are implemented | #4384 Dialogue strategiesbased on the user modeling are implemented in Kyoto city bus information system that has been developed at our laboratory. | ||
| </term> . The <term> stemming model </term> is | based | on <term> statistical machine translation | #4452 The stemming model is based on statistical machine translation and it uses an English stemmer and a small (10K sentences) parallel corpus as its sole training resources. | ||
| of lack of <term> negative feedback </term> . | Based | on these results , we present an <term> ECA | #5089 The distribution of nonverbal behaviors differed depending on the type of dialogue move being grounded, and the overall pattern reflected a monitoring of lack of negative feedback. Based on these results, we present an ECA that uses verbal and nonverbal grounding acts to update dialogue state. | ||
| algorithm </term> for <term> Arabic-English </term> | based | on <term> supervised training data </term> | #5286 This paper presents a maximum entropy word alignment algorithm for Arabic-Englishbased on supervised training data. | ||
| to automatically make these assignments | based | on a <term> discriminative training criterion | #5478 The model learns to automatically make these assignments based on a discriminative training criterion. | ||
| tech,14-6-H05-1064,ak | improvement </term> of [ ? ] 1.25 % beyond the <term> | base | parser </term> , and an [ ? ] 0.25 % improvement | #5541 The model gives an F-measure improvement of [?] 1.25% beyond thebase parser, and an [?] 0.25% improvement beyond the Collins (2000) reranker. | |
| statistical machine translation method </term> , | based | on <term> non-contiguous phrases </term> , | #5591 This paper presents a phrase-based statistical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps. | ||
| as well as a <term> training method </term> | based | on the <term> maximization </term> of <term> | #5632 A statistical translation model is also presented that deals such phrases, as well as a training methodbased on the maximization of translation accuracy, as measured with the NIST evaluation metric. | ||
| two-phase shift-reduce dependency parser </term> | based | on <term> SVM learning </term> . The <term> left-side | #6683 This paper proposes a two-phase shift-reduce dependency parserbased on SVM learning. | ||
| tech,7-10-I05-2048,ak | coupled with <term> rule-based and example | based | machine translation modules </term> to build | #6928 It has also successfully been coupled with rule-based and example based machine translation modules to build a multi engine machine translation system. |
