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

Spoken Question Answering (QA) is a key feature of voice assistants, usuallybacked by multiple QA systems. Users ask questions via spontaneous speech whichcan contain disfluencies, errors, and informal syntax or phrasing. This is amajor challenge in QA, causing unanswered questions or irrelevant answers, andleading to bad user experiences. We analyze failed QA requests to identify corechallenges: lexical gaps, proposition types, complex syntactic structure, andhigh specificity. We propose a Semantic Question Reformulation (SURF) modeloffering three linguistically-grounded operations (repair, syntactic reshaping,generalization) to rewrite questions to facilitate answering. Offlineevaluation on 1M unanswered questions from a leading voice assistant shows thatSURF significantly improves answer rates: up to 24% of previously unansweredquestions obtain relevant answers (75%). Live deployment shows positive impactfor millions of customers with unanswered questions; explicit relevancefeedback shows high user satisfaction.

Answering Unanswered Questions through Semantic Reformulations in Spoken QA