Text, Speech and Dialogue

The talk will concern several ideas that combat the sparse data problem of language modeling. All alleviate it, neither solves it. These ideas are: equivalence classification of histories, positional clustering (different cluster systems for different n-gram positions), use of linguistic classes (e.g., Wordnet), class constraints in maximum entropy estimation, random forests, and neural network classification. An interesting problem that must be faced is as follows: words that are sparse and need to be classified do not have sufficient statistics to indicate their appropriate class membership. V. Matoušek and P. Mautner (Eds.): TSD 2003, LNAI 2807, p. 1, 2003. c © Springer-Verlag Berlin Heidelberg 2003 Toward Robust Speech Recognition and Understanding