Papers by Yunfeng Zhang

2 papers
D2S: Document-to-Slide Generation Via Query-Based Text Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Existing research efforts to automate the document-to-slide generation process face a critical challenge: no publicly available dataset for training and benchmarking.
Approach: They propose a dataset SciDuet that gathers papers and their corresponding slides from recent years’ NLP and ML conferences.
Outcome: The proposed system outperforms state-of-the-art summarization baselines on both automated ROUGE metrics and qualitative human evaluation.
Rank-Aware Negative Training for Semi-Supervised Text Classification (2023.tacl-1)

Copied to clipboard

Challenge: Semi-supervised text classification-based paradigms employ the spirit of self-training, but the accuracy of pseudo-labels can be a problem in real-world scenarios.
Approach: They propose a Rank-aware Negative Training framework to address SSTC in noisy label learning . they rank unlabeled texts based on evidential support from the labeled texts.
Outcome: The proposed framework overcomes state-of-the-art alternatives and achieves competitive performance in other scenarios.

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