Bayesian Learning in Text Summarization

Tadashi Nomoto

Abstract: The paper presents a Bayesian model for text summarization, which explicitly encodes and exploits information on how human judgments are distributed over the text. Comparison is made against non Bayesian summarizers, using test data from Japanese news texts. It is found that the Bayesian approach generally leverages performance of a summarizer, at times giving it a significant lead over non-Bayesian models.