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

A bare meaning representation can be expressed in various ways using naturallanguage, depending on how the information is structured on the surface level.We are interested in finding ways to control topic-focus articulation whengenerating text from meaning. We focus on distinguishing active and passivevoice for sentences with transitive verbs. The idea is to add pragmaticinformation such as topic to the meaning representation, thereby forcing eitheractive or passive voice when given to a natural language generation system. Weuse graph neural models because there is no explicit information about wordorder in a meaning represented by a graph. We try three different methods fortopic-focus articulation (TFA) employing graph neural models for ameaning-to-text generation task. We propose a novel encoding strategy aboutnode aggregation in graph neural models, which instead of traditional encodingby aggregating adjacent node information, learns node representations by usingdepth-first search. The results show our approach can get competitiveperformance with state-of-art graph models on general text generation, and leadto significant improvements on the task of active-passive conversion comparedto traditional adjacency-based aggregation strategies. Different types of TFAcan have a huge impact on the performance of the graph models.

Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks