| model,10-2-H92-1016,bq | modelling </term> , the use of a <term> bigram | language | model </term> in conjunction with a <term> | #18720 These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. |
| tool,11-1-H92-1017,bq | recently added to the <term> Paramax spoken | language | understanding system </term> : <term> non-monotonic | #18820 This paper describes three relatively domain-independent capabilities recently added to the Paramax spoken language understanding system: non-monotonic reasoning, implicit reference resolution, and database query paraphrase. |
| model,3-1-H92-1026,bq | generative probabilistic model of natural | language | </term> , which we call <term> HBG </term> , | #18901 We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. |
| tech,9-1-H92-1095,bq | focuses on applying general-purpose <term> | language | understanding technology </term> to <term> | #19646 Language understanding work at Paramax focuses on applying general-purposelanguage understanding technology to spoken language understanding, text understanding, and document processing, integrating language understanding with speech recognition, knowledge-based information retrieval and image understanding. |
| other,12-1-A94-1017,bq | ( APs ) </term> for <term> real-time spoken | language | translation </term> . <term> Spoken language | #20207 This paper proposes a model using associative processors (APs) for real-time spoken language translation. |
| other,15-6-C94-1026,bq | which are selected from different <term> | language | families </term> . In <term> optical character | #20610 Most importantly, the experimental objects are Chinese-English texts, which are selected from differentlanguage families. |
| other,10-1-C94-1030,bq | speech recognition </term> of a <term> natural | language | </term> , it has been difficult to detect | #20624 In optical character recognition and continuous speech recognition of a natural language, it has been difficult to detect error characters which are wrongly deleted and inserted. |
| tech,4-1-C94-1061,bq | <term> concurrent , object-oriented natural | language | parsing </term> is introduced . Complete <term> | #20821 A grammar model for concurrent, object-oriented natural language parsing is introduced. |
| model,6-1-H94-1014,bq | paper introduces a simple mixture <term> | language | model </term> that attempts to capture <term> | #21217 This paper introduces a simple mixturelanguage model that attempts to capture long distance constraints in a sentence or paragraph. |
