Papers by Daoyuan Chen

3 papers
Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)

Copied to clipboard

Challenge: Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance.
Approach: They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning.
Outcome: The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.
Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for entity and relation extraction require light human annotation efforts.
Approach: They propose a method to re-label noisy instances with a cooperative group . they use a confidence consensus module to gather the wisdom of all agents .
Outcome: The proposed model outperforms state-of-the-art methods on two real-world datasets.
ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for chart summarization lack visual-language matching and reasoning ability.
Approach: They propose a method which synthesizes deep analysis based on chains of thought and strategies of context retrieval to improve the logical coherence and accuracy of the generated summaries.
Outcome: The proposed method outperforms 8 state-of-the-art models over 7 evaluation metrics and can significantly reduce time and cognitive resources required.

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