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

Generating a long, coherent text such as a paragraph requires a high-levelcontrol of different levels of relations between sentences (e.g., tense,coreference). We call such a logical connection between sentences as a(paragraph) flow. In order to produce a coherent flow of text, we explore twoforms of intersentential relations in a paragraph: one is a human-createdlinguistical relation that forms a structure (e.g., discourse tree) and theother is a relation from latent representation learned from the sentencesthemselves. Our two proposed models incorporate each form of relations intodocument-level language models: the former is a supervised model that jointlylearns a language model as well as discourse relation prediction, and thelatter is an unsupervised model that is hierarchically conditioned by arecurrent neural network (RNN) over the latent information. Our proposed modelswith both forms of relations outperform the baselines in partially conditionedparagraph generation task. Our codes and data are publicly available.

Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs