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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Knowledge base is one of the main forms to represent information in astructured way. A knowledge base typically consists of Resource DescriptionFrameworks (RDF) triples which describe the entities and their relations.Generating natural language description of the knowledge base is an importanttask in NLP, which has been formulated as a conditional language generationtask and tackled using the sequence-to-sequence framework. Current works mostlytrain the language models by maximum likelihood estimation, which tends togenerate lousy sentences. In this paper, we argue that such a problem ofmaximum likelihood estimation is intrinsic, which is generally irrevocable viachanging network structures. Accordingly, we propose a novel Triple-to-Text(T2T) framework, which approximately optimizes the inverse Kullback-Leibler(KL) divergence between the distributions of the real and generated sentences.Due to the nature that inverse KL imposes large penalty on fake-lookingsamples, the proposed method can significantly reduce the probability ofgenerating low-quality sentences. Our experiments on three real-world datasetsdemonstrate that T2T can generate higher-quality sentences and outperformbaseline models in several evaluation metrics.

Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence