We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Systems that interact with the user via natural language are in their infancy. As these systems mature and become more complex, it would be desirable for a system developer if the...
John Chen, Srinivas Bangalore, Owen Rambow, Marily...
Previous work on statistical language generation has primarily focused on grammaticality and naturalness, scoring generation possibilities according to a language model or user fe...
Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced ...
A trainable method for distinguishing between mathematics notation and natural language (here, English) in images of textlines, using computational geometry methods only with no a...