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

Coreference resolution is the task of identifying and grouping mentionsreferring to the same real-world entity. Previous neural models have mainlyfocused on learning span representations and pairwise scores for coreferencedecisions. However, current methods do not explicitly capture the referentialchoice in the hierarchical discourse, an important factor in coreferenceresolution. In this study, we propose a new approach that incorporatesrhetorical information into neural coreference resolution models. We collectrhetorical features from automated discourse parses and examine their impact.As a base model, we implement an end-to-end span-based coreference resolverusing a partially fine-tuned multilingual entity-aware language model LUKE. Weevaluate our method on the RuCoCo-23 Shared Task for coreference resolution inRussian. Our best model employing rhetorical distance between mentions hasranked 1st on the development set (74.6% F1) and 2nd on the test set (73.3% F1)of the Shared Task. We hope that our work will inspire further research onincorporating discourse information in neural coreference resolution models.

Light Coreference Resolution for Russian with Hierarchical Discourse Features