Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates...
Ezra Black, Frederick Jelinek, John D. Lafferty, D...
Parsing text to identify grammatical structure is a common task, especially in relation to programming languages and associated tools such as compilers. Parsers for context-free g...
We describe a method and its implementation for self-monitoring during natural language generation. In situations of communication where the generation of ambiguous utterances sho...
Abstract. A formal prosody description framework is introduced together with its relation to language semantics and NLP. The framework incorporates deep prosodic structures based o...