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

Improving user experience of a dialogue system often requires intensivedeveloper effort to read conversation logs, run statistical analyses, andintuit the relative importance of system shortcomings. This paper presents anovel approach to automated analysis of conversation logs that learns therelationship between user-system interactions and overall dialogue quality.Unlike prior work on utterance-level quality prediction, our approach learnsthe impact of each interaction from the overall user rating withoututterance-level annotation, allowing resultant model conclusions to be derivedon the basis of empirical evidence and at low cost. Our model identifiesinteractions that have a strong correlation with the overall dialogue qualityin a chatbot setting. Experiments show that the automated analysis from ourmodel agrees with expert judgments, making this work the first to show thatsuch weakly-supervised learning of utterance-level quality prediction is highlyachievable.

What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts