DFKI-LT - Using Syntactic and Semantic based Relations for Dialogue Act Recognition
Using Syntactic and Semantic based Relations for Dialogue Act Recognition
3 Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), Poster Session, Beijing, China, o.A., Association for Computational Linguistics, 2010
This paper presents a novel approach to dialogue act recognition employing multilevel information features. In addition to features such as context information and words in the utterances, the recognition task utilizes syntactic and semantic relations acquired by information extraction methods. These features are utilized by a Bayesian network classifier for our dialogue act recognition. The evaluation results show a clear improvement from the accuracy of the baseline (only with word features) with 61.9% to an accuracy of 67.4% achieved by the extended feature set.
Files: BibTeX, dialogueparis.pdf