Options
Examining the State-of-the-Art in News Timeline Summarization
Date Issued
2020-07-08
Date Available
2021-03-11T14:13:10Z
Abstract
Previous work on automatic news timeline summarization (TLS) leaves an unclear picture about how this task can generally be approached and how well it is currently solved. This is mostly due to the focus on individual subtasks, such as date selection and date summarization, and to the previous lack of appropriate evaluation metrics for the full TLS task. In this paper, we compare different TLS strategies using appropriate evaluation frameworks, and propose a simple and effective combination of methods that improves over the state-of-the-art on all tested benchmarks. For a more robust evaluation, we also present a new TLS dataset, which is larger and spans longer time periods than previous datasets.
Sponsorship
Irish Research Council
Science Foundation Ireland
Type of Material
Conference Publication
Web versions
Language
English
Status of Item
Peer reviewed
Part of
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Conference Details
The 58th Annual Meeting of the Association for Computational Linguistics, Online, 6-8 July 2020
This item is made available under a Creative Commons License
File(s)
Owning collection
Views
408
Last Month
1
1
Acquisition Date
Apr 18, 2024
Apr 18, 2024
Downloads
246
Last Month
4
4
Acquisition Date
Apr 18, 2024
Apr 18, 2024