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

Generating follow-up questions on the fly could significantly improveconversational survey quality and user experiences by enabling a more dynamicand personalized survey structure. In this paper, we proposed a novel task forknowledge-driven follow-up question generation in conversational surveys. Weconstructed a new human-annotated dataset of human-written follow-up questionswith dialogue history and labeled knowledge in the context of conversationalsurveys. Along with the dataset, we designed and validated a set ofreference-free Gricean-inspired evaluation metrics to systematically evaluatethe quality of generated follow-up questions. We then propose a two-stagedknowledge-driven model for the task, which generates informative and coherentfollow-up questions by using knowledge to steer the generation process. Theexperiments demonstrate that compared to GPT-based baseline models, ourtwo-staged model generates more informative, coherent, and clear follow-upquestions.

What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys