Details
Original language | English |
---|---|
Title of host publication | CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management |
Publication status | Published - 2015 |
Event | The 24th ACM International Conference on Information and Knowledge Management - Melbourne, Australia Duration: 19 Oct 2015 → 23 Oct 2015 Conference number: 24 |
Abstract
Keywords
- cs.IR, cs.CL, H.3.3
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. 2015.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research
}
TY - GEN
T1 - Balancing Novelty and Salience: Adaptive Learning to Rank Entities for Timeline Summarization of High-impact Events
AU - Tran, Tuan
AU - Niederée, Claudia
AU - Kanhabua, Nattiya
AU - Gadiraju, Ujwal
AU - Anand, Avishek
N1 - Conference code: 24
PY - 2015
Y1 - 2015
N2 - Long-running, high-impact events such as the Boston Marathon bombing often develop through many stages and involve a large number of entities in their unfolding. Timeline summarization of an event by key sentences eases story digestion, but does not distinguish between what a user remembers and what she might want to re-check. In this work, we present a novel approach for timeline summarization of high-impact events, which uses entities instead of sentences for summarizing the event at each individual point in time. Such entity summaries can serve as both (1) important memory cues in a retrospective event consideration and (2) pointers for personalized event exploration. In order to automatically create such summaries, it is crucial to identify the "right" entities for inclusion. We propose to learn a ranking function for entities, with a dynamically adapted trade-off between the in-document salience of entities and the informativeness of entities across documents, i.e., the level of new information associated with an entity for a time point under consideration. Furthermore, for capturing collective attention for an entity we use an innovative soft labeling approach based on Wikipedia. Our experiments on a real large news datasets confirm the effectiveness of the proposed methods.
AB - Long-running, high-impact events such as the Boston Marathon bombing often develop through many stages and involve a large number of entities in their unfolding. Timeline summarization of an event by key sentences eases story digestion, but does not distinguish between what a user remembers and what she might want to re-check. In this work, we present a novel approach for timeline summarization of high-impact events, which uses entities instead of sentences for summarizing the event at each individual point in time. Such entity summaries can serve as both (1) important memory cues in a retrospective event consideration and (2) pointers for personalized event exploration. In order to automatically create such summaries, it is crucial to identify the "right" entities for inclusion. We propose to learn a ranking function for entities, with a dynamically adapted trade-off between the in-document salience of entities and the informativeness of entities across documents, i.e., the level of new information associated with an entity for a time point under consideration. Furthermore, for capturing collective attention for an entity we use an innovative soft labeling approach based on Wikipedia. Our experiments on a real large news datasets confirm the effectiveness of the proposed methods.
KW - cs.IR
KW - cs.CL
KW - H.3.3
U2 - 10.1145/2806416.2806486
DO - 10.1145/2806416.2806486
M3 - Conference contribution
SN - 978-1-4503-3794-6
BT - CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management
T2 - The 24th ACM International Conference on Information and Knowledge Management
Y2 - 19 October 2015 through 23 October 2015
ER -