Machine Learning of Generic and User-Focused Summarization

TL;DR

This paper introduces a machine learning approach to optimize salience functions for text summarization, effectively addressing both generic and user-focused summarization tasks by learning from document-abstract pairs.

Contribution

It presents a novel machine learning method to automatically discover optimal feature combinations for salience functions in text summarization, applicable to both generic and user-specific summaries.

Findings

Successfully learned salience functions for different summarization types

Improved summarization quality through feature optimization

Applicable to diverse summarization tasks

Abstract

A key problem in text summarization is finding a salience function which determines what information in the source should be included in the summary. This paper describes the use of machine learning on a training corpus of documents and their abstracts to discover salience functions which describe what combination of features is optimal for a given summarization task. The method addresses both "generic" and user-focused summaries.