Dialogue act classification using language models

Pragmatically important information as e.g. dialogue acts that describe the illocution of an utterance depend in traditional processing approaches on error prone syntactic /semantic processing. We present a statistically based method for dialogue act classification that has word strings as input. An experimental evaluation shows that this method can be successfully used to determine dialogue acts. The overall recognition rate in the experiments is in the range of 65%--67% for German test data, and 74% for an experiment with English dialogues. 1. INTRODUCTION For spoken or typed language processing systems, it is often important to extract just the core intention of a sentence. The classes are sometimes described as dialogue moves 3 or, as in the VERBMOBIL system, as dialogue acts 1. In the latter system which translates spoken time scheduling dialogues of two humans 2 these dialogue acts classify sentences e.g. as ACCEPT, REJECT, SUGGEST. They are used e.g. in a shallow transla...