Paper: Learning Information Status Of Discourse Entities

ACL ID W06-1612
Title Learning Information Status Of Discourse Entities
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2006
  • Malvina Nissim (CNR-Institute of Cognitive Sciences and Technology, Rome Italy)

In this paper we address the issue of au- tomatically assigning information status to discourse entities. Using an annotated cor- pus of conversational English and exploit- ing morpho-syntactic and lexical features, we train a decision tree to classify entities introduced by noun phrases as old, medi- ated, or new. We compare its performance with hand-crafted rules that are mainly based on morpho-syntactic features and closely relate to the guidelines that had been used for the manual annotation. The decision tree model achieves an overall ac- curacyof79.5%, significantlyoutperform- ing the hand-crafted algorithm (64.4%). We also experiment with binary classifica- tions by collapsing in turn two of the three target classes into one and retraining the model.