Papers by Wenjie Ou

1 papers
Effective Unsupervised Constrained Text Generation based on Perturbed Masking (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for constrained text generation stochastically sample edit positions and actions, which cause unnecessary search steps.
Approach: They propose to extend perturbed masking technique to search for most incongruent token to edit and introduce four multi-aspect scoring functions to select edit action to further reduce search difficulty.
Outcome: The proposed method achieves state-of-the-art in two representative tasks . it does not require supervised data, so it could be applied to different generation tasks.

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