TY - GEN
T1 - Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
AU - Li, Manling
AU - Ma, Tengfei
AU - Yu, Mo
AU - Wu, Lingfei
AU - Gao, Tian
AU - Ji, Heng
AU - McKeown, Kathleen
N1 - Funding Information:
This research is based upon work in part supported by U.S. DARPA KAIROS Program No. FA8750-19-2-1004, FA8750-19-C-0206, the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract No. FA8650-17-C-9116. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of DARPA, ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged. Previous methods generally generate summaries separately for each date after they determine the key dates of events. These methods overlook the events' intra-structures (arguments) and inter-structures (event-event connections). Following a different route, we propose to represent the news articles as an event-graph, thus the summarization task becomes compressing the whole graph to its salient sub-graph. The key hypothesis is that the events connected through shared arguments and temporal order depict the skeleton of a timeline, containing events that are semantically related, structurally salient, and temporally coherent in the global event graph. A time-aware optimal transport distance is then introduced for learning the compression model in an unsupervised manner. We show that our approach significantly improves the state of the art on three real-world datasets, including two public standard benchmarks and our newly collected Timeline100 dataset.
AB - Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged. Previous methods generally generate summaries separately for each date after they determine the key dates of events. These methods overlook the events' intra-structures (arguments) and inter-structures (event-event connections). Following a different route, we propose to represent the news articles as an event-graph, thus the summarization task becomes compressing the whole graph to its salient sub-graph. The key hypothesis is that the events connected through shared arguments and temporal order depict the skeleton of a timeline, containing events that are semantically related, structurally salient, and temporally coherent in the global event graph. A time-aware optimal transport distance is then introduced for learning the compression model in an unsupervised manner. We show that our approach significantly improves the state of the art on three real-world datasets, including two public standard benchmarks and our newly collected Timeline100 dataset.
UR - http://www.scopus.com/inward/record.url?scp=85127415954&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127415954&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85127415954
T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 6443
EP - 6456
BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -