Papers with supervise student model training

1 papers
Distilling Multilingual Transformers into CNNs for Scalable Intent Classification (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing multilingual models for voice assistants are limited by their prohibitive inference time and limited performance.
Approach: They propose to distill and deploy multilingual Transformer models for voice assistants using a teacher-student framework that uses teacher-trained models to supervise student model training.
Outcome: The proposed model outperforms a teacher model trained on unlabelled data and achieves equivalent performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations