Discovering Typical Histories of Entities by Multi-Timeline Summarization

Duan, Yijun; Jatowt, Adam; Tanaka, Katsumi

doi:10.1145/3078714.3078725

Cited by 6 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We detect the temporal expressions by using spaCy 5 tool. We adopt this extraction method motivated by the previous work [3,8]. However, when preprocessing datasets, more refined methods for associating time with sentences could be applied (e.g., [16]).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Discovering Latent Threads in Entity Histories

2019

Self Cite

View full text Add to dashboard Cite

Knowledge of entity histories is often necessary for comprehensive understanding and characterization of entities. Yet, the analysis of an entity's history is often most meaningful when carried out in comparison with the histories of other entities. In this paper, we describe a novel task of history-based entity categorization and comparison. Based on a set of entity-related documents which are assumed as an input, we determine latent entity categories whose members share similar histories; hence, we are effectively grouping entities based on the correspondences in their historical developments. Next, we generate comparative timelines for each determined group allowing users to elucidate similarities and differences in the histories of entities. We evaluate our approach on several datasets of different entity types demonstrating its effectiveness against competitive baselines.

show abstract

Section: Discussionmentioning

confidence: 99%

“…To analyze how the number of categories k affects the quality of identified exemplars, we investigate how Ratio and AveImp vary per-k. Figure 3b shows the results. Recall that the number of exemplars is equal to the number of categories and k is set in the range [2,8].…”

Section: ) Effects Of the Number Of Latent Categoriesmentioning

confidence: 99%

Discovering Latent Threads in Entity Histories

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Methods relying on event detection such as Ge et al (2015); Minard et al (2015); Bedi et al (2017) often evaluate their system in terms of Precision, Recall and F1-measure. However, most projects often lack datasets and must then resort to human evaluation as in Duan et al (2017); Swan and Allan (2000); Tran et al (2015a).…”

Section: Timeline Summarizationmentioning

confidence: 99%

“…TLS is a subfield of the Multi-Document Summarization (MDS) task and has been studied extensively in the NLP community: for instance, Swan and Allan (2000) generate clusters of Named Entities and noun chunks that best describe major news topics covered in a subset of the TDT-2 dataset (Allan et al, 1998), which contains text transcripts of broadcast news spanning from January 1, 1998, to June 30, 1998, in English;Nguyen et al (2014) generate timelines by detecting events that are the most relevant to a user query. They apply their methodology on a dataset of newswire texts in English covering the 2004-2011 period provided by the AFP French news agency; Duan et al (2017) extend these methods to summarize the common history of similar entities such as Japanese Cities or French scientists. Examples of timelines generated by such methods are shown in Figure 1.…”

Section: Introduction 1exploring Archivesmentioning

confidence: 99%

Archive TimeLine Summarization (ATLS): Conceptual Framework for Timeline Generation over Historical Document Collections

Guillaume¹,

Doucet²,

Jatowt³

2023

Preprint

View full text Add to dashboard Cite

Archive collections are nowadays mostly available through search engines interfaces, which allow a user to retrieve documents by issuing queries. The study of these collections may be, however, impaired by some aspects of search engines, such as the overwhelming number of documents returned or the lack of contextual knowledge provided. New methods that could work independently or in combination with search engines are then required to access these collections. In this position paper, we propose to extend TimeLine Summarization (TLS) methods on archive collections to assist in their studies. We provide an overview of existing TLS methods and we describe a conceptual framework for an Archive TimeLine Summarization (ATLS) system, which aims to generate informative, readable and interpretable timelines.

show abstract

“…10 https://yurikopia.com/disco/ events [1], the characteristics of life events that are highly transformative and iconic [2], and the systematic differences in life structure across groups [3], etc. In particular, Wikipedia has been used extensively, for the task of disambiguition of named entities [34], [35], the recognition of biographical sentences [36], the identification of latent biographical structure [8], and the summarization of typical life trajactories and events [37], [38], etc.…”

Section: Related Workmentioning

confidence: 99%