Building Event-Centric Knowledge Graphs from News

Rospocher, Marco; Erp, Marieke van; Vossen, Piek; Fokkens, Antske; Aldabe, Itziar; Rigau, Germán; Soroa, Aitor; Ploeger, Thomas; Bogaard, Tessel

doi:10.2139/ssrn.3199233

Cited by 12 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frameworks and models for understanding narratives have mainly focused on fictional texts (Lehnert, 1981;Goyal et al, 2010;Mani, 2012) Modern day news reports still reflect narrative structures but they have proven difficult for automatic tools (Rospocher et al, 2016). To the best of our knowledge, previous work on StoryLine Extraction is limited, if we exclude the contribution by Caselli and Vossen (2016).…”

Section: Related Workmentioning

confidence: 99%

The Event StoryLine Corpus: A New Benchmark for Causal and Temporal Relation Extraction

Caselli¹,

Vossen²

2017

Proceedings of the Events and Stories in the News Workshop

Self Cite

View full text Add to dashboard Cite

This paper reports on the Event StoryLine Corpus (ESC) v0.9, a new benchmark dataset for the temporal and causal relation detection. By developing this dataset, we also introduce a new task, the StoryLine Extraction from news data, which aims at extracting and classifying events relevant for stories, from across news documents spread in time and clustered around a single seminal event or topic. In addition to describing the dataset, we also report on three baselines systems whose results show the complexity of the task and suggest directions for the development of more robust systems.

show abstract

Section: Related Workmentioning

confidence: 99%

The Event StoryLine Corpus: A New Benchmark for Causal and Temporal Relation Extraction

Caselli¹,

Vossen²

2017

Proceedings of the Events and Stories in the News Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…Event-Centric Knowledge Graphs (ECKG) Rospocher et al, 2016) is another related work which represent news articles as graphs. Event nodes are linked to DBPedia (Auer et al, 2007), with the goal of enriching entities and events with dynamic knowledge.…”

Section: Multi-documentmentioning

confidence: 99%

A Consolidated Open Knowledge Representation for Multiple Texts

Wities¹,

Shwartz²,

Stanovsky³

et al. 2017

Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics

View full text Add to dashboard Cite

We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open textbased manner. We do so by consolidating OIE extractions using entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to give semantic applications an easy handle on consolidated information across multiple texts.

show abstract

“…Identical or coreferring concepts are collapsed in a single node. Rospocher et al (2016) present a more supervised approach where concepts in the graph are linked to DBPedia 1 entries. This along with other metadata is used to detect coreferences and disambiguate concepts.…”

Section: Consolidated Representationmentioning

confidence: 99%