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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Evaluating and understanding the inappropriateness of chatbot behaviors canbe challenging, particularly for chatbot designers without technicalbackgrounds. To democratize the debugging process of chatbot misbehaviors fornon-technical designers, we propose a framework that leverages dialogue act(DA) modeling to automate the evaluation and explanation of chatbot responseinappropriateness. The framework first produces characterizations ofcontext-aware DAs based on discourse analysis theory and real-worldhuman-chatbot transcripts. It then automatically extracts features to identifythe appropriateness level of a response and can explain the causes of theinappropriate response by examining the DA mismatch between the response andits conversational context. Using interview chatbots as a testbed, ourframework achieves comparable classification accuracy with higherexplainability and fewer computational resources than the deep learningbaseline, making it the first step in utilizing DAs for chatbot responseappropriateness evaluation and explanation.

Democratizing Chatbot Debugging: A Computational Framework for Evaluating and Explaining Inappropriate Chatbot Responses