A corpus-based approach to topic in Danish dialog

Abstract

We report on an investigation of the pragmatic category of topic in Danish dialog and its correlation to surface features of NPs. Using a corpus of 444 utterances, we trained a decision tree system on 16 features. The system achieved nearhuman performance with success rates of 84-89% and F 1-scores of 0.63-0.72 in 10-fold cross validation tests (human performance: 89% and 0.78). The most important features turned out to be preverbal position, definiteness, pronominalisation, and non-subordination. We discovered that NPs in epistemic matrix clauses (e.g. "I think . . . ") were seldom topics and we suspect that this holds for other interpersonal matrix clauses as well. © 2005 Association for Computational Linguistics.