2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/33216We present an empirical investigation of various ways to automatically identify phrases in a tagged corpus that are useful for dialogue act tagging. We found that a new method (which measures a phrase's deviation from an optimally-predictive phrase), enhanced with a lexical filtering mechanism, produces significantly better cues than manually-selected cue phrases, the exhaustive set of phrases in a training corpus, and phrases chosen by traditional metrics, like mutual information and information gain.14 pages, published in PACLING'99Artificial IntelligenceMachine LearningI.2.7; I.2.6text