This paper presents an empirical study for improving the performance of text chunking. We focus on two issues: the problem of selecting feature spaces, and the problem of alleviat...
Grounded language models represent the relationship between words and the non-linguistic context in which they are said. This paper describes how they are learned from large corpo...
Word sense discrimination is an unsupervised clustering problem, which seeks to discover which instances of a word/s are used in the same meaning. This is done strictly based on i...
We address the problem of improving the efficiency of natural language text input under degraded conditions (for instance, on PDAs or cell phones or by disabled users) by taking a...
Weintroducea formalcontext mechanism,embeddedinto a descriptionlogicsframework,whichis ableto uniformly represent and managedifferent formsof ambiguitiesas theyoccurin the courseo...