時間線摘要化是一個過程，可以從有關特定主題(例如"H1N1")的新聞文 章中濃縮出重要事件並分配相應的時間戳記。為了實現這一目標，傳統方法通 常根據相關報導的數量和事件提及的頻率來確定事件的重要性。然而，這些方 法往往忽略了對主角的追 ，即影響事件結果並指導敘事焦點的主要實體或角 色，因此錯過了他們對事件重要性的實質性影響。為了彌補這一缺口，我們引 入了一種新的策略，稱為PIECE，通過依存關係識別主角，並在多方面的時 間動態圖的幫助下捕捉圍繞不同主角的觀點隨時間變化的情況。我們的實驗表 明，PIECE在跨不同語言數據集的時間線摘要化任務中表現優於以前的方法。

Timeline summarization is a process to condense essential events from news articles regarding a specified topic, such as “H1N1”, and assign corresponding timestamps. To achieve this, traditional methods determined the significance of events based on the number of associated reports and the frequency of event references. However, these methods often neglect to track the development of protagonists, the primary entities or actors who impact event outcomes and direct the narrative focus, thus missing their substantial influence on event importance. To bridge this gap, we introduce PIECE, a novel strategy that identifies protagonists through dependency relations and captures shifting perspectives centered around various protagonist over time, with the aid of a multi-faceted temporal dynamic graph. Our experiments demonstrate that PIECE outperforms previous methods in the date selection task for timeline summarization across different languages datasets.

Abstract (Chinese) ............................ I
Acknowledgements (Chinese) ............................ II
Abstract ............................ III
Contents ............................ IV
List of Figures ............................ VI
List of Tables ............................ VII
1 Introduction ............................ 1
2 Related Work ............................ 6
2.1 Clustering-based: ............................ 6
2.2 Graph-based: .............................. 7
3 Methodology ............................ 8
3.1 Overview................................. 8
3.2 ClaimExtraction ............................ 10
3.3 Query-awareGraphLearning ..................... 13
3.4 ProtagonistsDetection ......................... 17
3.5 Multi-facetedTemporalGraphLearning . . . . . . . . . . . . . . . 20
3.6 AggregationbyChangePointsDetection . . . . . . . . . . . . . . . 25
4 Experiments 28
4.1 ExperimentalSetup........................... 28
4.2 Datasets................................. 29
4.2.1 Englishdatasets......................... 29
4.2.2 MandarinDataset........................ 29
4.3 ExperimentalResults.......................... 30
4.3.1 ResultsonEnglishdatasets .................. 30
4.3.2 ResultsonMandarindatasets ................. 31
4.4 SummarizationAnalyze ........................ 32
5 Conclusion & Future Work 38
Bibliography 40

R. Swan and J. Allan, “Automatic generation of overview timelines,” in Pro- ceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’00, (New York, NY, USA), p. 49–56, Association for Computing Machinery, 2000.
R. Yan, L. Kong, C. Huang, X. Wan, X. Li, and Y. Zhang, “Timeline gen- eration through evolutionary trans-temporal summarization,” in Proceedings of the 2011 Conference on Empirical Methods in Natural Language Process- ing, (Edinburgh, Scotland, UK.), pp. 433–443, Association for Computational Linguistics, July 2011.
J. Steen and K. Markert, “Abstractive timeline summarization,” in Proceedings of the 2nd Workshop on New Frontiers in Summarization, (Hong Kong, China), pp. 21–31, Association for Computational Linguistics, Nov. 2019.

G. Tran, E. Herder, and K. Markert, “Joint graphical models for date selection in timeline summarization,” in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), (Beijing, China), pp. 1598–1607, Association for Computational Linguistics, July 2015
Y. Yu, A. Jatowt, A. Doucet, K. Sugiyama, and M. Yoshikawa, “Multi- TimeLine summarization (MTLS): Improving timeline summarization by generating multiple summaries,” in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), (Online), pp. 377–387, Association for Computational Linguistics, Aug. 2021.
M. Li, T. Ma, M. Yu, L. Wu, T. Gao, H. Ji, and K. McKeown, “Timeline summarization based on event graph compression via time-aware optimal transport,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, (Online and Punta Cana, Dominican Republic), pp. 6443–6456, Association for Computational Linguistics, Nov. 2021
R. Mihalcea and P. Tarau, “TextRank: Bringing order into text,” in Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, (Barcelona, Spain), pp. 404–411, Association for Computational Linguistics, July 2004.
M. Honnibal and I. Montani, “spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing.” To appear, 2017.
D. Vannella, T. Flati, and R. Navigli, “WoSIT: A word sense induction toolkit for search result clustering and diversification,” in Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demon- strations, (Baltimore, Maryland), pp. 67–72, Association for Computational Linguistics, June 2014.
N. Reimers and I. Gurevych, “Sentence-bert: Sentence embeddings using siamese bert-networks,” in Proceedings of the 2019 Conference on Empiri- cal Methods in Natural Language Processing, Association for Computational Linguistics, 11 2019.
B. J. Frey and D. Dueck, “Clustering by Passing Messages Between Data Points,” Science, vol. 315, pp. 972–976, Feb. 2007.
S. Robertson and H. Zaragoza, “The probabilistic relevance framework: Bm25 and beyond,” Found. Trends Inf. Retr., vol. 3, p. 333–389, apr 2009.
L. Page, S. Brin, R. Motwani, and T. Winograd, “The pagerank citation ranking: Bringing order to the web.,” Technical Report 1999-66, Stanford InfoLab, November 1999. Previous number = SIDL-WP-1999-0120.
Y. Lin, H. Ji, F. Huang, and L. Wu, “A joint neural model for information extraction with global features,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, (Online), pp. 7999–8009, Association for Computational Linguistics, July 2020.
Q. Ning, S. Subramanian, and D. Roth, “An improved neural baseline for temporal relation extraction,” in Proceedings of the 2019 Conference on Empir- ical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), (Hong Kong, China), pp. 6203–6209, Association for Computational Linguistics, Nov. 2019.
T. N. Kipf and M. Welling, “Variational graph auto-encoders,” NIPS Workshop on Bayesian Deep Learning, 2016.
W.-j. Wang, C.-J. Chen, C.-y. Lai, C.-m. Lee, and H.-h. Lin, “A chinese math word problem solving system based on linguistic theory and non-statistical approach,” in Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020), pp. 208–222, 2020.
S. Huang, Y. Hitti, G. Rabusseau, and R. Rabbany, “Laplacian change point detection for dynamic graphs,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 349– 358, 2020.

H. L. Chieu and Y. K. Lee, “Query based event extraction along a timeline,” in Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’04, (New York, NY, USA), p. 425–432, Association for Computing Machinery, 2004.

D. Gholipour Ghalandari and G. Ifrim, “Examining the state-of-the-art in news timeline summarization,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, (Online), pp. 1322–1334, Association for Computational Linguistics, July 2020.
G. Binh Tran, M. Alrifai, and D. Quoc Nguyen, “Predicting relevant news events for timeline summaries,” in Proceedings of the 22nd International Conference on World Wide Web, WWW ’13 Companion, (New York, NY,
USA), p. 91–92, Association for Computing Machinery, 2013.

G. Tran, M. Alrifai, and E. Herder, “Timeline summarization from relevant headlines,” in Advances in Information Retrieval (A. Hanbury, G. Kazai, A. Rauber, and N. Fuhr, eds.), (Cham), pp. 245–256, Springer International Publishing, 2015.