Papers by Lee Hsun Hsieh

1 papers
Enconter: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer (2021.eacl-main)

Copied to clipboard

Challenge: Autoregressive language models do not perform well under hard lexical constraints as they lack fine control of content generation process.
Approach: They propose a new insertion transformer that considers hard lexical constraints and imposes rules over objects in the generated text.
Outcome: The proposed model outperforms baseline models in several performance metrics rendering it more suitable in practical applications.

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