Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2014

Abstract

Story highlights form a succinct single-document summary consisting of 3-4 highlight sentences that reflect the gist of a news article. Automatically producing news highlights is very challenging. We propose a novel method to improve news highlights extraction by using microblogs. The hypothesis is that microblog posts, although noisy, are not only indicative of important pieces of information in the news story, but also inherently “short and sweet” resulting from the artificial compression effect due to the length limit. Given a news article, we formulate the problem as two rank-then-extract tasks: (1) we find a set of indicative tweets and use them to assist the ranking of news sentences for extraction; (2) we extract top ranked tweets as a substitute of sentence extraction. Results based on our news-tweets pairing corpus indicate that the method significantly outperform some strong baselines for single-document summarization.

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of 25th International Conference on Computational Linguistics (COLING 2014)

First Page

872

Last Page

883

Publisher

Association for Computational Linguistics

City or Country

Dublin, Ireland

Additional URL

https://aclweb.org/anthology/C14-1083

Download

Share

COinS