Article Structure
Abstract
We study the use of temporal information in the form of timelines to enhance multi-document summarization.
Introduction
There has been a good amount of research invested into improving the temporal interpretation of text.
Related Work
Barzilay et al.
Methodology
To incorporate temporal information into multi-document summarization, we adopt the workflow in Figure 3, which has two key processes: 1) temporal processing, and 2) summarization.
Experiments and Results
The proposed timeline features and TIMEMMR were implemented on top of SWING, and evaluated on the test documents from TAC-2011 (Owczarzak and Dang, 2011).
Discussion
We now examine the proposed 1) timeline features, 2) TIMEMMR algorithm, and 3) reliability filtering metric in greater detail to gain insight into their efficacy.
Conclusion
We have shown in this work how temporal information in the form of timelines can be incorporated into multi-document summarization.
Topics
significant improvements
- Compared to a competitive baseline, significant improvements of up to 4.1% are obtained.Page 2, “Introduction”
- A statistically significant improvement of 4.1% is obtained with the use of all three features over SWING.Page 6, “Experiments and Results”
- to guide the use of timelines such that significant improvements in R-2 over SWING are obtained.Page 7, “Experiments and Results”
See all papers in Proc. ACL 2014 that mention significant improvements.
See all papers in Proc. ACL that mention significant improvements.
Back to top.
