← Search

Akash Veeragouni

1 accepted papers

2022

Distilling Multilingual Transformers into CNNs for Scalable Intent Classification

EMNLP 2022industry

We describe an application of Knowledge Distillation used to distill and deploy multilingual Transformer models for voice assistants, enabling text classification for customers globally. Transformers have set new state-of-the-art results for tasks like intent classification, and multilingual models…

Cited by 2SourcePDFScholar