When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
Extractive summarization techniques cannot generate document summaries shorter than a single sentence, something that is often required. An ideal summarization system would unders...
Michele Banko, Vibhu O. Mittal, Michael J. Witbroc...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...
Integrating several legacy software systems together is commonly performed with multiple applications of the Adapter Design Pattern in oo languages such as Java. The integration i...
We propose a domain specific model for statistical machine translation. It is wellknown that domain specific language models perform well in automatic speech recognition. We show ...