Joint Extraction of Events and Entities within a Document Context

Yang, Bishan; Mitchell, Tom M.

doi:10.18653/v1/n16-1033

Cited by 175 publications

(180 citation statements)

References 13 publications

Supporting

Mentioning

177

Contrasting

Unclassified

Order By: Relevance

“…Since the ACE data set lacks coreference annotations, we train on the coreference annotations from the OntoNotes dataset (Pradhan et al, 2012). For event extraction we use the split described in Yang and Mitchell (2016); Zhang et al (2019). We refer to this split as ACE05-E in what follows.…”

Section: Methodsmentioning

confidence: 99%

Entity, Relation, and Event Extraction with Contextualized Span Representations

Wadden¹,

Wennberg²,

Luan³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

406

298

View full text Add to dashboard Cite

We examine the capabilities of a unified, multitask framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DYGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (withinsentence) and global (cross-sentence) context. Our framework achieves state-of-theart results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform well at capturing relationships among entities in the same or adjacent sentences, while dynamic span graph updates model long-range crosssentence relationships. For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions. Our code is publicly available at https://github. com/dwadden/dygiepp and can be easily adapted for new tasks or datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Entity, Relation, and Event Extraction with Contextualized Span Representations

Wadden¹,

Wennberg²,

Luan³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

406

298

View full text Add to dashboard Cite

show abstract

“…Duan et al (2017) introduces a pretrained document embedding to aid event detection, but their extraction is still at the sentence level. Past work on cross-sentence extraction often relies on explicit coreference annotations or the assumption of a single event in the document (Wick et al, 2006;Gerber and Chai, 2010;Swampillai and Stevenson, 2011;Yoshikawa et al, 2011;Koch et al, 2014;Yang and Mitchell, 2016). Recently, there has been increasing interest in general cross-sentence relation extraction Peng et al, 2017;Wang and Poon, 2018), but their scope is still limited to short text spans of a few consecutive sentences.…”

Section: Document-level Relation Extractionmentioning

confidence: 99%

Document-Level N-ary Relation Extraction with Multiscale Representation Learning

Jia¹,

Wong²,

Poon³

2019

Proceedings of the 2019 Conference of the North

106

View full text Add to dashboard Cite

Most information extraction methods focus on binary relations expressed within single sentences. In high-value domains, however, n-ary relations are of great demand (e.g., drug-genemutation interactions in precision oncology). Such relations often involve entity mentions that are far apart in the document, yet existing work on cross-sentence relation extraction is generally confined to small text spans (e.g., three consecutive sentences), which severely limits recall. In this paper, we propose a novel multiscale neural architecture for documentlevel n-ary relation extraction. Our system combines representations learned over various text spans throughout the document and across the subrelation hierarchy. Widening the system's purview to the entire document maximizes potential recall. Moreover, by integrating weak signals across the document, multiscale modeling increases precision, even in the presence of noisy labels from distant supervision. Experiments on biomedical machine reading show that our approach substantially outperforms previous n-ary relation extraction methods.

show abstract

“…We implemented a state-of-the-art event detection system based on Yang and Mitchell (2016) to pinpoint words or phrases in a sentence that refer to events involving participants and locations, affected by other events and spatiotemporal aspects. The module is trained on the ACE 2005 data (Doddington et al 2004), consisting of 529 documents from a variety of sources.…”

Section: Monolingual and Cross-lingual Event Detectionmentioning

confidence: 99%

Different Types of Automated and Semi-automated Semantic Storytelling: Curation Technologies for Different Sectors

Rehm

Schneider

Bourgonje

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Many industries face an increasing need for smart systems that support the processing and generation of digital content. This is both due to an ever increasing amount of incoming content that needs to be processed faster and more efficiently, but also due to an ever increasing pressure of publishing new content in cycles that are getting shorter and shorter. In a research and technology transfer project we develop a platform that provides content curation services that can be integrated into Content Management Systems, among others. In the project we develop curation services, which comprise semantic text and document analytics processes as well as knowledge technologies that can be applied to document collections. The key objective is to support digital curators in their daily work, i.e., to (semi-)automate processes that the human experts are normally required to carry out intellectually and, typically, without tool support. The goal is to enable knowledge workers to become more efficient and more effective as well as to produce high-quality content. In this article we focus on the current state of development with regard to semantic storytelling in our four use cases.

show abstract

Joint Extraction of Events and Entities within a Document Context

Cited by 175 publications

References 13 publications

Entity, Relation, and Event Extraction with Contextualized Span Representations

Entity, Relation, and Event Extraction with Contextualized Span Representations

Document-Level N-ary Relation Extraction with Multiscale Representation Learning

Different Types of Automated and Semi-automated Semantic Storytelling: Curation Technologies for Different Sectors

Contact Info

Product

Resources

About