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

Measuring user satisfaction level is a challenging task, and a criticalcomponent in developing large-scale conversational agent systems serving theneeds of real users. An widely used approach to tackle this is to collect humanannotation data and use them for evaluation or modeling. Human annotation basedapproaches are easier to control, but hard to scale. A novel alternativeapproach is to collect user's direct feedback via a feedback elicitation systemembedded to the conversational agent system, and use the collected userfeedback to train a machine-learned model for generalization. User feedback isthe best proxy for user satisfaction, but is not available for some ineligibleintents and certain situations. Thus, these two types of approaches arecomplementary to each other. In this work, we tackle the user satisfactionassessment problem with a hybrid approach that fuses explicit user feedback,user satisfaction predictions inferred by two machine-learned models, onetrained on user feedback data and the other human annotation data. The hybridapproach is based on a waterfall policy, and the experimental results withAmazon Alexa's large-scale datasets show significant improvements in inferringuser satisfaction. A detailed hybrid architecture, an in-depth analysis on userfeedback data, and an algorithm that generates data sets to properly simulatethe live traffic are presented in this paper.

Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents