Papers by Claudia Shi

1 papers
An Invariant Learning Characterization of Controlled Text Generation (2023.acl-long)

Copied to clipboard

Challenge: Controlled generation is a problem of creating text that contains stylistic or semantic attributes of interest.
Approach: They propose a distribution shift-based control system that can be used to train a predictor of the desired attribute.
Outcome: The proposed method shows that the most effective predictor should be invariant across multiple text environments.

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