Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
Latent Semantic Analysis is used in many research fields with several applications of classifications. We propose to improve LSA with additional semantic information found with s...
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP withou...
Shallow semantic parsing, the automatic identification and labeling of sentential constituents, has recently received much attention. Our work examines whether semantic role info...
: Performance of Natural Language Interface often deteriorates due to linguistic phenomena of Semantic Symmetry and Ambiguous Modification (Katz and Lin, 2003). In this paper we pr...