This paper describes the design and application of time-enhanced, finite state models of discourse cues to the automated segmentation of broadcast news. We describe our analysis o...
Lexical selection is a significant problem for widecoverage machine translation: depending on the context, a given source language word can often be translated into different targ...
We believe that language is a complex adaptive system that emerges from adaptive interactions between language users and continues to evolve and adapt through repeated interaction...
In general, a certain range of sentences in a text, is widely assumed to form a coherent unit which is called a discourse segment. Identifying the segment boundaries is a first st...
Maximum entropy framework proved to be expressive and powerful for the statistical language modelling, but it suffers from the computational expensiveness of the model building. T...