Papers by Dandan Tao

2 papers
TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks (2022.lrec-1)

Copied to clipboard

Challenge: Approximately 1 in 6 Americans (or 48 million people) are sickened by foodborne illness each year.
Approach: They propose to use Twitter's TWEET-FID dataset to create annotated datasets for multiple foodborne illness incident detection tasks.
Outcome: The proposed dataset is the first publicly available annotated dataset for multiple foodborne illness incident detection tasks.
Let Modalities Teach Each Other: Modal-Collaborative Knowledge Extraction and Fusion for Multimodal Knowledge Graph Completion (2025.findings-naacl)

Copied to clipboard

Challenge: Recent studies have focused on missing triples in knowledge graphs, but lack correlation between modalities.
Approach: They propose a framework to foster mutual guidance and collaboration in unimodal knowledge extraction and multimodal knowledge fusion.
Outcome: Extensive experiments on three real-world datasets demonstrate advantages of Moodle over state-of-the-art methods.

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