Papers by Luheng Wang

1 papers
Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models (2022.findings-acl)

Copied to clipboard

Challenge: Sequence-to-sequence models fail to generalize in hierarchy-sensitive manner when performing syntactic transformations.
Approach: They evaluate whether seq2seq models generalize hierarchically on two transformations . they use pre-trained models and their multilingual variants to test their generalization .
Outcome: The proposed models generalize hierarchically on two transformations in English and German.

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