Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
This study examines the relationship between two kinds of semantic spaces -- i.e., spaces based on term frequency (tf) and word cooccurrence frequency (co) -- and four semantic re...
Document classification presents difficult challenges due to the sparsity and the high dimensionality of text data, and to the complex semantics of the natural language. The tradi...
In this paper we investigate the task of automatically identifying the correct argument structure for a set of verbs. The argument structure of a verb allows us to predict the rel...
The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...