We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a rec...
Constructing a program from a specification is a long-known general and fundamental problem. Besides its theoretical interest, this question also has practical implications, since...
The most critical issue in generating and recognizing paraphrases is development of wide-coverage paraphrase knowledge. Previous work on paraphrase acquisition has collected lexic...
Graphical languages of various sorts are increasingly used for the specification and the design of high-integrity real-time systems. Their coverage however does not extend with a...
We study the use of rich syntax-based statistical models for generating grammatical case for the purpose of machine translation from a language which does not indicate case explic...