SIGdial 2012

13th Annual SIGdial Meeting on Discourse and Dialogue

A Reranking Model for Discourse Segmentation using Subtree Features

Presented by:
Ngo Xuan Bach
Ngo Xuan Bach, Nguyen Le Minh, Akira Shimazu

This paper presents a discriminative reranking model for the discourse segmentation task, the first step in a discourse parsing system. Our model exploits subtree features to rerank Nbest outputs of a base segmenter, which uses syntactic and lexical features in a CRF framework. Experimental results on the RST Discourse Treebank corpus show that our model outperforms existing discourse segmenters in both settings that use gold standard Penn Treebank parse trees and Stanford parse trees.