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

This work aims to build a dialogue agent that can weave new factual contentinto conversations as naturally as humans. We draw insights from linguisticprinciples of conversational analysis and annotate human-human conversationsfrom the Switchboard Dialog Act Corpus to examine humans strategies foracknowledgement, transition, detail selection and presentation. When currentchatbots (explicitly provided with new factual content) introduce facts into aconversation, their generated responses do not acknowledge the prior turns.This is because models trained with two contexts - new factual content andconversational history - generate responses that are non-specific w.r.t. one ofthe contexts, typically the conversational history. We show that specificityw.r.t. conversational history is better captured by Pointwise ConditionalMutual Information ($\text{pcmi}_h$) than by the established use of PointwiseMutual Information ($\text{pmi}$). Our proposed method, Fused-PCMI, trades off$\text{pmi}$ for $\text{pcmi}_h$ and is preferred by humans for overall qualityover the Max-PMI baseline 60% of the time. Human evaluators also judgeresponses with higher $\text{pcmi}_h$ better at acknowledgement 74% of thetime. The results demonstrate that systems mimicking human conversationaltraits (in this case acknowledgement) improve overall quality and more broadlyillustrate the utility of linguistic principles in improving dialogue agents.

Human-like informative conversations: Better acknowledgements using conditional mutual information