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

The goal of building intelligent dialogue systems has largely been separatelypursued under two paradigms: task-oriented dialogue (TOD) systems, whichperform goal-oriented functions, and open-domain dialogue (ODD) systems, whichfocus on non-goal-oriented chitchat. The two dialogue modes can potentially beintertwined together seamlessly in the same conversation, as easily done by afriendly human assistant. Such ability is desirable in conversational agents,as the integration makes them more accessible and useful. Our paper addressesthis problem of fusing TODs and ODDs in multi-turn dialogues. Based on thepopular TOD dataset MultiWOZ, we build a new dataset FusedChat, by rewritingthe existing TOD turns and adding new ODD turns. This procedure constructsconversation sessions containing exchanges from both dialogue modes. Itfeatures inter-mode contextual dependency, i.e., the dialogue turns from thetwo modes depend on each other. Rich dependency patterns including co-referenceand ellipsis are features. The new dataset, with 60k new human-written ODDturns and 5k re-written TOD turns, offers a benchmark to test a dialoguemodel's ability to perform inter-mode conversations. This is a more challengingtask since the model has to determine the appropriate dialogue mode andgenerate the response based on the inter-mode context. But such models wouldbetter mimic human-level conversation capabilities. We evaluate baseline modelson this task, including classification-based two-stage models and two-in-onefused models. We publicly release FusedChat and the baselines to propel futurework on inter-mode dialogue systems https://github.com/tomyoung903/FusedChat.

Fusing task-oriented and open-domain dialogues in conversational agents