Papers by Hadrien Glaude

1 papers
A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification (D19-61)

Copied to clipboard

Challenge: Recent studies have focused on the problem of generalizing from a few examples per category.
Approach: They propose to use feature space data augmentation methods to improve intent classification performance in few-shot setting.
Outcome: The proposed methods improve intent classification performance in few-shot setting beyond transfer learning approaches.

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