Event graphs for information retrieval and multi-document summarization

Glavaš, Goran; Šnajder, Jan

doi:10.1016/j.eswa.2014.04.004

Cited by 81 publications

(42 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The G-FLOW (Christensen et al, 2013) is a system for coherent extractive multidocument summarization that generates an ordered summary by optimizing the coherence and salient factors, where the coherence of text is evaluated by an approximated discourse graph. Glavaš andŠnajder (2014) introduce an event based summarization method that exploits the strength of machine learning rule based approaches and performs effectively on the event oriented document collection.…”

Section: A Graph Based Methodsmentioning

confidence: 99%

A Review on Text Summarization Techniques

Verma¹,

Verma²

2020

JSR

View full text Add to dashboard Cite

In recent years, an enormous amount of text data from diversified sources has been emerged day-by-day. This huge amount of data carries essential information and knowledge that needs to be effectively summarized to be useful. Hence, the main contribution of this paper is twofold. We first introduce some concepts related to extractive text summarization and then provide a systematic analysis of various text summarization techniques. In particular, some challenges in extractive summarization of single as well as multiple documents are introduced. The problems focus on the textual assessment and similarity measurement between the text documents are addressed. The challenges discussed are generic and applicable to every possible scenario in text summarization. Then, existing state-of-the-art of extractive summarization techniques are discussed that focus on the identified challenges.

show abstract

Section: A Graph Based Methodsmentioning

confidence: 99%

A Review on Text Summarization Techniques

Verma¹,

Verma²

2020

JSR

View full text Add to dashboard Cite

show abstract

“…Glavaš andŠnajder [13] proposed an event-based text representation; however it only has temporal relation. ZhaoMan and Zong-Tian [14] proposed event lattice to represent narrative texts based on concept lattice.…”

Section: Event-oriented Text Representationmentioning

confidence: 99%

Prior Knowledge-Based Event Network for Chinese Text

Shi

Shan

Liu

et al. 2017

International Journal of Digital Multimedia Broadcasting

View full text Add to dashboard Cite

Text representation is a basic issue of text information processing and event plays an important role in text understanding; both attract the attention of scholars. The event network conceals lexical relations in events, and its edges express logical relations between events in document. However, the events and relations are extracted from event-annotated text, which makes it hard for largescale text automatic processing. In the paper, with expanded CEC (Chinese Event Corpus) as data source, prior knowledge of manifestation rules of event and relation as the guide, we propose an event extraction method based on knowledge-based rule of event manifestation, to achieve automatic building and improve text processing performance of event network.

show abstract

“…However, few attempts have focused on the use of automatic techniques for event classification for summarization systems for the news domain [1]. In fact, most of the work on multi-document summarization are either based on Centrality- [6,7,8,9], and Coveragebase methods [10,11,12,13,1,14,15].…”

Section: Introductionmentioning

confidence: 99%

“…In fact, most of the work on multi-document summarization are either based on Centrality- [6,7,8,9], and Coveragebase methods [10,11,12,13,1,14,15]. Generally, centrality-based models are used to generate generic summaries, the MMR family generates query-oriented ones, and coverage-based models produce summaries driven by topics or events.…”

Section: Introductionmentioning

confidence: 99%

“…The use of event information in multi-document summarization can be ar- 15 ranged in the following categories: initial hand-based experiments [16]; pattern-based approaches based on enriched representations of sentences, such as the cases of the work presented by Zhang et al [15] and by Wenjie Li et al [13], which define events using an event key term and a set of related entities, or centrality-based approaches working over an event-driven representation of 20 the input [1], where events are also pattern-based defined; and, clusteringbased event definition [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring events and distributed representations of text in multi-document summarization

Marujo

Ribeiro

Gershman

et al. 2016

Knowledge-Based Systems

View full text Add to dashboard Cite

In this article, we explore an event detection framework to improve multidocument summarization. Our approach is based on a two-stage single-document method that extracts a collection of key phrases, which are then used in a centrality-as-relevance passage retrieval model. We explore how to adapt this single-document method for multi-document summarization methods that are able to use event information. The event detection method is based on Fuzzy

show abstract

Event graphs for information retrieval and multi-document summarization

Cited by 81 publications

References 28 publications

A Review on Text Summarization Techniques

A Review on Text Summarization Techniques

Prior Knowledge-Based Event Network for Chinese Text

Exploring events and distributed representations of text in multi-document summarization

Contact Info

Product

Resources

About