Papers by Ryan A. Cook

1 papers
No Simple Answer to Data Complexity: An Examination of Instance-Level Complexity Metrics for Classification Tasks (2025.naacl-long)

Copied to clipboard

Challenge: Understanding data complexity at the instance level has become increasingly important in Natural Language Processing (NLP) and machine learning (ML).
Approach: They empirically examine the relationship between instance-level complexity scores and metric selection for classification tasks.
Outcome: The results show that storing training loss provides similar complexity rankings to other methods, but not demographic fairness, even in downstream predictions.

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