Baldridge, J. and A. Lascarides [2005] Probabilistic Head-Driven Parsing for Discourse Structure, in Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNNL), Ann Arbor.
We describe a data-driven approach to building interpretable discourse structures for appointment scheduling dialogues. We represent discourse structures as headed trees and model them with probabilistic head-driven parsing techniques. We show that dialogue-based features regarding turn-taking and domain specific goals have a large positive impact on performance. Our best model achieves an f-score of 43.2% for labelled discourse relations and 67.9% for unlabelled ones, significantly beating a right-branching baseline that uses the most frequent relations.
@inproceedings{baldridge:lascarides:2005a,
author = {Jason Baldridge and Alex Lascarides},
year = {2005},
title = {Probabilistic Head-Driven Parsing for Discourse Structure},
booktitle = {Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL)}
}