preprint Open access

Intent Detection with WikiHow

  • arXiv (Cornell University)
  • Cornell University
Research footprint

At a glance

Citations
12
References
17
Comments
0
Paper overview

Abstract

Modern task-oriented dialog systems need to reliably understand users' intents. Intent detection is most challenging when moving to new domains or new languages, since there is little annotated data. To address this challenge, we present a suite of pretrained intent detection models. Our models are able to predict a broad range of intended goals from many actions because they are trained on wikiHow, a comprehensive instructional website. Our models achieve state-of-the-art results on the Snips dataset, the Schema-Guided Dialogue dataset, and all 3 languages of the Facebook multilingual dialog datasets. Our models also demonstrate strong zero- and few-shot performance, reaching over 75% accuracy using only 100 training examples in all datasets.

Record transparency

Publication details

DOI
10.48550/arxiv.2009.05781
OpenAlex
W3114186958
Document type
preprint
Language
EN
Source
arXiv (Cornell University)
Last metadata update
Community

Comments

Log in to join the discussion.

  1. No comments yet. Start the discussion.