Intent Detection with WikiHow
This addresses the data scarcity problem in intent detection for dialog systems, though it appears incremental as it builds on existing pretraining approaches with a new data source.
The paper tackles the challenge of intent detection in task-oriented dialog systems when moving to new domains or languages with limited annotated data by presenting pretrained models trained on wikiHow, achieving state-of-the-art results on multiple datasets and over 75% accuracy with only 100 training examples.
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.