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

Building document-grounded dialogue systems have received growing interest asdocuments convey a wealth of human knowledge and commonly exist in enterprises.Wherein, how to comprehend and retrieve information from documents is achallenging research problem. Previous work ignores the visual property ofdocuments and treats them as plain text, resulting in incomplete modality. Inthis paper, we propose a Layout-aware document-level Information Extractiondataset, LIE, to facilitate the study of extracting both structural andsemantic knowledge from visually rich documents (VRDs), so as to generateaccurate responses in dialogue systems. LIE contains 62k annotations of threeextraction tasks from 4,061 pages in product and official documents, becomingthe largest VRD-based information extraction dataset to the best of ourknowledge. We also develop benchmark methods that extend the token-basedlanguage model to consider layout features like humans. Empirical results showthat layout is critical for VRD-based extraction, and system demonstration alsoverifies that the extracted knowledge can help locate the answers that userscare about.

Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration