Probabilistic Head-Driven Parsing for Discourse Structure

Jason Baldridge,A. Lascarides

Published 2005 in Conference on Computational Natural Language Learning

ABSTRACT

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.

PUBLICATION RECORD

  • Publication year

    2005

  • Venue

    Conference on Computational Natural Language Learning

  • Publication date

    2005-06-01

  • Fields of study

    Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

CITED BY

Showing 1-64 of 64 citing papers · Page 1 of 1