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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Document-level discourse parsing, in accordance with the Rhetorical StructureTheory (RST), remains notoriously challenging. Challenges include the deepstructure of document-level discourse trees, the requirement of subtle semanticjudgments, and the lack of large-scale training corpora. To address suchchallenges, we propose to exploit robust representations derived from multiplelevels of granularity across syntax and semantics, and in turn incorporate suchrepresentations in an end-to-end encoder-decoder neural architecture for moreresourceful discourse processing. In particular, we first use a pre-trainedcontextual language model that embodies high-order and long-range dependency toenable finer-grain semantic, syntactic, and organizational representations. Wefurther encode such representations with boundary and hierarchical informationto obtain more refined modeling for document-level discourse processing.Experimental results show that our parser achieves the state-of-the-artperformance, approaching human-level performance on the benchmarked RSTdataset.

An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations