Papers with unified information extraction

2 papers
General Collaborative Framework between Large Language Model and Experts for Universal Information Extraction (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing unified information extraction approaches face challenges such as noise interference, abstract label semantics, and diverse span granularity.
Approach: They propose a general Collaborative Information Extraction framework to address these challenges in universal information extraction tasks.
Outcome: The proposed framework is based on a general Recognizer and task-specific Experts for recognizing predefined types and extracting spans respectively.
Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases (2024.findings-emnlp)

Copied to clipboard

Challenge: Definition bias is a negative phenomenon that can mislead models.
Approach: They propose a framework that measures definition bias, bias-aware fine-tuning and task-specific bias mitigation to mitigate definition bias in information extraction.
Outcome: The proposed framework mitigates definition bias in information extraction tasks by measuring definition bias, bias-aware fine-tuning, and task-specific bias mitigation.

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