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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We study the problem of providing recommended responses to customer serviceagents in live-chat dialogue systems. Smart-reply systems have been widelyapplied in real-world applications (e.g. Gmail, LinkedIn Messaging), where mostof them can successfully recommend reactive responses. However, we observe amajor limitation of current methods is that they generally have difficulties insuggesting proactive investigation act (e.g. "Do you perhaps have anotheraccount with us?") due to the lack of long-term context information, whichindeed act as critical steps for customer service agents to collect informationand resolve customers' issues. Thus in this work, we propose an end-to-endmethod with special focus on suggesting proactive investigative questions tocustomer agents in Airbnb's customer service live-chat system. Effectiveness ofour proposed method can be validated through qualitative and quantitativeresults.

Beyond "How may I help you?": Assisting Customer Service Agents with Proactive Responses