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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

This paper provides a comprehensive analysis of the first shared task onEnd-to-End Natural Language Generation (NLG) and identifies avenues for futureresearch based on the results. This shared task aimed to assess whether recentend-to-end NLG systems can generate more complex output by learning fromdatasets containing higher lexical richness, syntactic complexity and diversediscourse phenomena. Introducing novel automatic and human metrics, we compare62 systems submitted by 17 institutions, covering a wide range of approaches,including machine learning architectures -- with the majority implementingsequence-to-sequence models (seq2seq) -- as well as systems based ongrammatical rules and templates. Seq2seq-based systems have demonstrated agreat potential for NLG in the challenge. We find that seq2seq systemsgenerally score high in terms of word-overlap metrics and human evaluations ofnaturalness -- with the winning SLUG system (Juraska et al., 2018) beingseq2seq-based. However, vanilla seq2seq models often fail to correctly expressa given meaning representation if they lack a strong semantic control mechanismapplied during decoding. Moreover, seq2seq models can be outperformed byhand-engineered systems in terms of overall quality, as well as complexity,length and diversity of outputs. This research has influenced, inspired andmotivated a number of recent studies outwith the original competition, which wealso summarise as part of this paper.

Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge