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

Audio-Visual Scene-Aware Dialog (AVSD) is an extension from Video QuestionAnswering (QA) whereby the dialogue agent is required to generate naturallanguage responses to address user queries and carry on conversations. This isa challenging task as it consists of video features of multiple modalities,including text, visual, and audio features. The agent also needs to learnsemantic dependencies among user utterances and system responses to makecoherent conversations with humans. In this work, we describe our submission tothe AVSD track of the 8th Dialogue System Technology Challenge. We adoptdot-product attention to combine text and non-text features of input video. Wefurther enhance the generation capability of the dialogue agent by adoptingpointer networks to point to tokens from multiple source sequences in eachgeneration step. Our systems achieve high performance in automatic metrics andobtain 5th and 6th place in human evaluation among all submissions.

Multimodal Transformer with Pointer Network for the DSTC8 AVSD Challenge