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

Building an open-domain conversational agent is a challenging problem.Current evaluation methods, mostly post-hoc judgments of static conversation,do not capture conversation quality in a realistic interactive context. In thispaper, we investigate interactive human evaluation and provide evidence for itsnecessity; we then introduce a novel, model-agnostic, and dataset-agnosticmethod to approximate it. In particular, we propose a self-play scenario wherethe dialog system talks to itself and we calculate a combination of proxiessuch as sentiment and semantic coherence on the conversation trajectory. Weshow that this metric is capable of capturing the human-rated quality of adialog model better than any automated metric known to-date, achieving asignificant Pearson correlation (r>.7, p<.05). To investigate the strengths ofthis novel metric and interactive evaluation in comparison to state-of-the-artmetrics and human evaluation of static conversations, we perform extendedexperiments with a set of models, including several that make novelimprovements to recent hierarchical dialog generation architectures throughsentiment and semantic knowledge distillation on the utterance level. Finally,we open-source the interactive evaluation platform we built and the dataset wecollected to allow researchers to efficiently deploy and evaluate dialogmodels.

Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems