An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

Code

• github.com/clinc/oos-eval
  OfficialIn papernone★ 0
• github.com/thuiar/textoir
  pytorch★ 243
• github.com/thuiar/textoir-demo
  pytorch★ 55
• github.com/Abdulk084/Intent_classification
  none★ 0
• github.com/farbodtaymouri/BERT-GAN
  none★ 0

Abstract

Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover every example. We introduce a new dataset that includes queries that are out-of-scope---i.e., queries that do not fall into any of the system's supported intents. This poses a new challenge because models cannot assume that every query at inference time belongs to a system-supported intent class. Our dataset also covers 150 intent classes over 10 domains, capturing the breadth that a production task-oriented agent must handle. We evaluate a range of benchmark classifiers on our dataset along with several different out-of-scope identification schemes. We find that while the classifiers perform well on in-scope intent classification, they struggle to identify out-of-scope queries. Our dataset and evaluation fill an important gap in the field, offering a way of more rigorously and realistically benchmarking text classification in task-driven dialog systems.

Tasks

Reproductions