TU Darmstadt / ULB / TUbiblio

Real-Time News Summarization with Adaptation to Media Attention

Rücklé, Andreas and Gurevych, Iryna (2017):
Real-Time News Summarization with Adaptation to Media Attention.
In: Proceedings of the 11th Conference on Recent Advances in Natural Language Processing (RANLP 2017), Association for Computational Linguistics, Varna, Bulgaria, DOI: 10.26615/978-954-452-049-6_079,
[Online-Edition: https://doi.org/10.26615/978-954-452-049-6_079],
[Conference or Workshop Item]

Abstract

Real-time summarization of news events (RTS) allows persons to stay up-to-date on important topics that develop over time. With the occurrence of major sub-events, media attention increases and a large number of news articles are published. We propose a summarization approach that detects such changes and selects a suitable summarization configuration at run-time. In particular, at times with high media attention, our approach exploits the redundancy in content to produce a more precise summary and avoid emitting redundant information. We find that our approach significantly outperforms a strong non-adaptive RTS baseline in terms of the emitted summary updates and achieves the best results on a recent web-scale dataset. It can successfully be applied to a different real-world dataset without requiring additional modifications.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Rücklé, Andreas and Gurevych, Iryna
Title: Real-Time News Summarization with Adaptation to Media Attention
Language: English
Abstract:

Real-time summarization of news events (RTS) allows persons to stay up-to-date on important topics that develop over time. With the occurrence of major sub-events, media attention increases and a large number of news articles are published. We propose a summarization approach that detects such changes and selects a suitable summarization configuration at run-time. In particular, at times with high media attention, our approach exploits the redundancy in content to produce a more precise summary and avoid emitting redundant information. We find that our approach significantly outperforms a strong non-adaptive RTS baseline in terms of the emitted summary updates and achieves the best results on a recent web-scale dataset. It can successfully be applied to a different real-world dataset without requiring additional modifications.

Title of Book: Proceedings of the 11th Conference on Recent Advances in Natural Language Processing (RANLP 2017)
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_p_QAEduInf
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Varna, Bulgaria
Date Deposited: 11 Jul 2017 19:26
DOI: 10.26615/978-954-452-049-6_079
Official URL: https://doi.org/10.26615/978-954-452-049-6_079
Identification Number: TUD-CS-2017-0181
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item