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

Intelligent conversational assistants, such as Apple's Siri, Microsoft'sCortana, and Amazon's Echo, have quickly become a part of our digital life.However, these assistants have major limitations, which prevents users fromconversing with them as they would with human dialog partners. This limits ourability to observe how users really want to interact with the underlyingsystem. To address this problem, we developed a crowd-powered conversationalassistant, Chorus, and deployed it to see how users and workers would interacttogether when mediated by the system. Chorus sophisticatedly converses with endusers over time by recruiting workers on demand, which in turn decide whatmight be the best response for each user sentence. Up to the first month of ourdeployment, 59 users have held conversations with Chorus during 320conversational sessions. In this paper, we present an account of Chorus'deployment, with a focus on four challenges: (i) identifying when conversationsare over, (ii) malicious users and workers, (iii) on-demand recruiting, and(iv) settings in which consensus is not enough. Our observations could assistthe deployment of crowd-powered conversation systems and crowd-powered systemsin general.

"Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent