Papers by Yunfan Yang

2 papers
Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template (D19-55)

Copied to clipboard

Challenge: Recent approaches for paraphrasing generate unpredictable results .
Approach: They propose a question paraphrasing pipeline model based on templates that identifies template and retrieves candidate templates and fills them with original topic words.
Outcome: The proposed model outperforms the seq2seq model on two datasets and is more promising when the training sample is small.
CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation (2026.acl-long)

Copied to clipboard

Challenge: Tables contain rich structured information, but when stored as images their contents remain "locked" within pixels.
Approach: They propose a framework that disentangles optimization across LaTeX tables components . CSPO assigns component-specific rewards and backpropagates each signal through tokens .
Outcome: The proposed framework disentangles optimization across LaTeX tables components—structure, style, and content.

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