We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
In this paper, an efficient method for language model lookahead probability generation is presented. Traditional methods generate language model look-ahead (LMLA) probabilities fo...
We consider the problem of learning factored probabilistic CCG grammars for semantic parsing from data containing sentences paired with logical-form meaning representations. Tradi...
Tom Kwiatkowski, Luke S. Zettlemoyer, Sharon Goldw...
DryadLINQ is a system and a set of language extensions that enable a new programming model for large scale distributed computing. It generalizes previous execution environments su...
Yuan Yu, Michael Isard, Dennis Fetterly, Mihai Bud...