Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...
This paper presents a linguistic framework for developing a formal knowledge acquisition method. The framework is intended to empower domain experts to specify information require...
Ghang Lee, Charles M. Eastman, Rafael Sacks, Shamk...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Model programs represent transition systems that are used fy expected behavior of systems at a high level of abstraction. The main application area is application-level network pro...
Background: Interest is growing in the application of syntactic parsers to natural language processing problems in biology, but assessing their performance is difficult because di...