English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Established cross-document coreference resolution (CDCR) datasets containevent-centric coreference chains of events and entities with identityrelations. These datasets establish strict definitions of the coreferencerelations across related tests but typically ignore anaphora with more vaguecontext-dependent loose coreference relations. In this paper, we qualitativelyand quantitatively compare the annotation schemes of ECB+, a CDCR dataset withidentity coreference relations, and NewsWCL50, a CDCR dataset with a mix ofloose context-dependent and strict coreference relations. We propose a phrasingdiversity metric (PD) that encounters for the diversity of full phrases unlikethe previously proposed metrics and allows to evaluate lexical diversity of theCDCR datasets in a higher precision. The analysis shows that coreference chainsof NewsWCL50 are more lexically diverse than those of ECB+ but annotating ofNewsWCL50 leads to the lower inter-coder reliability. We discuss the differenttasks that both CDCR datasets create for the CDCR models, i.e., lexicaldisambiguation and lexical diversity. Finally, to ensure generalizability ofthe CDCR models, we propose a direction for CDCR evaluation that combines CDCRdatasets with multiple annotation schemes that focus of various properties ofthe coreference chains.

Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes