Corpus ID: 227151540

Cross-Document Event Coreference Resolution Beyond Corpus-Tailored Systems

@article{Bugert2020CrossDocumentEC,
  title={Cross-Document Event Coreference Resolution Beyond Corpus-Tailored Systems},
  author={Michael Bugert and N. Reimers and Iryna Gurevych},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.12249}
}
Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multi-document applications, but despite recent progress on corpora and model development, downstream improvements from applying CDCR have not been shown yet. The reason lies in the fact that every CDCR system released to date was developed, trained, and tested only on a single respective corpus… Expand

References

SHOWING 1-10 OF 48 REFERENCES
Revisiting the Evaluation for Cross Document Event Coreference
  • 8
  • Highly Influential
  • PDF
Unsupervised Event Coreference Resolution
  • 50
  • PDF
Entity-Based Cross-Document Coreferencing Using the Vector Space Model
  • 599
  • PDF
...
1
2
3
4
5
...