Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants

Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query. Accurately tagging a query as out-of-domain is particularly hard in scenarios when the chatbot is not equipped to handle a topic wh...

Full description

Saved in:
Bibliographic Details
Main Authors Qian, Cheng, Qi, Haode, Wang, Gengyu, Kunc, Ladislav, Potdar, Saloni
Format Journal Article
LanguageEnglish
Published 16.01.2023
Subjects
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query. Accurately tagging a query as out-of-domain is particularly hard in scenarios when the chatbot is not equipped to handle a topic which has semantic overlap with an existing topic it is trained on. We propose a simple yet effective OOS detection method that outperforms standard OOS detection methods in a real-world deployment of virtual assistants. We discuss the various design and deployment considerations for a cloud platform solution to train virtual assistants and deploy them at scale. Additionally, we propose a collection of datasets that replicates real-world scenarios and show comprehensive results in various settings using both offline and online evaluation metrics.
DOI:10.48550/arxiv.2301.06544