With the need to make sense out of large and constantly growing information spaces, tools to support information management are becoming increasingly valuable. In prior work we pr...
Corpus-based stochastic language models have achieved significant success in speech recognition, but construction of a corpus pertaining to a specific application is a difficult ta...
We have designed, implemented, and proved the correctness of a compiler generator that accepts action semantic descriptions of imperative programming languages. The generated comp...
We investigate the effectiveness of selftraining PCFG grammars with latent annotations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared to...
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...