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

Topic segmentation and outline generation strive to divide a document intocoherent topic sections and generate corresponding subheadings. Such a processunveils the discourse topic structure of a document that benefits quicklygrasping and understanding the overall context of the document from a higherlevel. However, research and applications in this field have been restraineddue to the lack of proper paragraph-level topic representations andlarge-scale, high-quality corpora in Chinese compared to the success achievedin English. Addressing these issues, we introduce a hierarchicalparagraph-level topic structure representation with title, subheading, andparagraph that comprehensively models the document discourse topic structure.In addition, we ensure a more holistic representation of topic distributionwithin the document by using sentences instead of keywords to representsub-topics. Following this representation, we construct the largest ChineseParagraph-level Topic Structure corpus (CPTS), four times larger than thepreviously largest one. We also employ a two-stage man-machine collaborativeannotation method to ensure the high quality of the corpus both in form andsemantics. Finally, we validate the computability of CPTS on two fundamentaltasks (topic segmentation and outline generation) by several strong baselines,and its efficacy has been preliminarily confirmed on the downstream task:discourse parsing. The representation, corpus, and benchmark we establishedwill provide a solid foundation for future studies.

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark