Query based event extraction along a timeline

Chieu, Hai Leong; Lee, Yoong Keok

doi:10.1145/1008992.1009065

Cited by 101 publications

(85 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical studies in this domain include Swan and Allan [24], Allan et al [1], Chieu at al. [6], Yan et al [27], Tran et al [4]. These studies share the same approach of extracting the most relevant and descriptive sentences from the full article texts.…”

Section: Related Workmentioning

confidence: 99%

“…The articles focus on long-span stories on the armed conflicts Egypt Revolution, Syria War, Yemen Crisis and Libya War 6 . News articles We collected news articles by simulating users searching for articles relevant for the timelines of the aforementioned news stories -for this purpose, we used Google and targeted the same 24 news agencies that were used for creating the timelines used as the ground truth.…”

Section: Dataset and Experimental Settingmentioning

confidence: 99%

“…Chieu et al [6] utilize the popularity of a sentence on date t i as the sum of TF-IDF similarity scores with other sentences that are published in around t i +-k days to estimate how important this sentence is. We select k=10, following the author's setting.…”

Section: Systems For Comparisonmentioning

confidence: 99%

“…News agencies often manually construct and maintain timelines for major events, but constructing such visual summaries often requires a considerable amount of human effort and does not scale well. Existing approaches for TS aim to tackle one of two problems: (i) select a subset of important dates as the major points of the timeline (e.g, [12], [4]) and/or (ii) generate a good daily summary for each of these dates (e.g, [6], [27], [4]). In this study, we set our focus on the second problem.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Timeline Summarization from Relevant Headlines

Tran

Alrifai

Herder

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Timeline summaries are an effective way for helping newspaper readers to keep track of long-lasting news stories, such as the Egypt revolution. A good timeline summary provides a concise description of only the main events, while maintaining good understandability. As manual construction of timelines is very time-consuming, there is a need for automatic approaches. However, automatic selection of relevant events is challenging due to the large amount of news articles published every day. Furthermore, current state-of-the-art systems produce summaries that are suboptimal in terms of relevance and understandability. We present a new approach that exploits the headlines of online news articles instead of the articles' full text. The quantitative and qualitative results from our user studies confirm that our method outperforms state-of-the-art system in these aspects.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Dataset and Experimental Settingmentioning

confidence: 99%

Section: Systems For Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Timeline Summarization from Relevant Headlines

Tran

Alrifai

Herder

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…When to assimilate?. Events occur over a timeline [Chieu and Lee 2004]. Timeline refers to a measurable span of time with information denoted at designated points.…”

Section: Introductionmentioning

confidence: 99%

Information assimilation framework for event detection in multimedia surveillance systems

2006

View full text Add to dashboard Cite

Most multimedia surveillance and monitoring systems nowadays utilize multiple types of sensors to detect events of interest as and when they occur in the environment. However, due to the asynchrony among and diversity of sensors, information assimilation -how to combine the information obtained from asynchronous and multifarious sources is an important and challenging research problem. In this paper, we propose a framework for information assimilation that addresses the issues -"when", "what" and "how" to assimilate the information obtained from different media sources in order to detect events in multimedia surveillance systems. The proposed framework adopts a hierarchical probabilistic assimilation approach to detect atomic and compound events. To detect an event, our framework uses not only the media streams available at the current instant but it also utilizes their two important properties -first, accumulated past history of whether they have been providing concurring or contradictory evidences, and -second, the system designer's confidence in them. The experimental results show the utility of the proposed framework.

show abstract

Cross Document Event Clustering Using Knowledge Mining from Co-reference Chains

Kuo

Chen

2005

Information Retrieval Technology

View full text Add to dashboard Cite

Unifying terminology usages which captures more term semantics is useful for event clustering. This paper proposes a metric of normalized chain edit distance to mine, incrementally, controlled vocabulary from cross-document co-reference chains. Controlled vocabulary is employed to unify terms among different co-reference chains. A novel threshold model that incorporates both time decay function and spanning window uses the controlled vocabulary for event clustering on streaming news. Under correct co-reference chains, the proposed system has a 15.97% performance increase compared to the baseline system, and a 5.93% performance increase compared to the system without introducing controlled vocabulary. Furthermore, a Chinese co-reference resolution system with a chain filtering mechanism is used to experiment on the robustness of the proposed event clustering system. The clustering system using noisy co-reference chains still achieves a 10.55% performance increase compared to the baseline system. The above shows that our approach is promising.

show abstract

Query based event extraction along a timeline

Cited by 101 publications

References 11 publications

Timeline Summarization from Relevant Headlines

Timeline Summarization from Relevant Headlines

Information assimilation framework for event detection in multimedia surveillance systems

Cross Document Event Clustering Using Knowledge Mining from Co-reference Chains

Contact Info

Product

Resources

About