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

This paper proposes a framework to address the issue of data scarcity inDocument-Grounded Dialogue Systems(DGDS). Our model leverages high-resourcelanguages to enhance the capability of dialogue generation in low-resourcelanguages. Specifically, We present a novel pipeline CLEM (Cross-LingualEnhanced Model) including adversarial training retrieval (Retriever andRe-ranker), and Fid (fusion-in-decoder) generator. To further leveragehigh-resource language, we also propose an innovative architecture to conductalignment across different languages with translated training. Extensiveexperiment results demonstrate the effectiveness of our model and we achieved4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as asolution to resource scarcity in DGDS and provide useful guidance formulti-lingual alignment tasks.

Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages