PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
Minwoo Jeong and Ivan Titov
In: ACL 2010, 11-16 July 2010, Uppsala, Sweden.


Documents often have inherently parallel structure: they may consist of a text and commentaries, or an abstract and a body, or parts presenting alternative views on the same problem. Revealing relations between the parts by jointly segmenting and predicting links between the segments, would help to visualize such documents and construct friendlier user interfaces. To address this problem, we propose an unsupervised Bayesian model for joint discourse segmentation and alignment. We apply our method to the “English as a second language” podcast dataset where each episode is composed of two parallel parts: a story and an explanatory lecture. The predicted topical links uncover hidden relations between the stories and the lectures. In this domain, our method achieves competitive results, rivaling those of a previously proposed supervised technique.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:7826
Deposited By:Ivan Titov
Deposited On:17 March 2011