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

Query rewriting (QR) systems are widely used to reduce the friction caused byerrors in a spoken language understanding pipeline. However, the underlyingsupervised models require a large number of labeled pairs, and these pairs arehard and costly to be collected. Therefore, We propose an augmentationframework that learns patterns from existing training pairs and generatesrewrite candidates from rewrite labels inversely to compensate for insufficientQR training data. The proposed framework casts the augmentation problem as asequence-to-sequence generation task and enforces the optimization process witha policy gradient technique for controllable rewarding. This approach goesbeyond the traditional heuristics or rule-based augmentation methods and is notconstrained to generate predefined patterns of swapping/replacing words. Ourexperimental results show its effectiveness compared with a fully trained QRbaseline and demonstrate its potential application in boosting the QRperformance on low-resource domains or locales.

Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems