More than Classification: A Unified Framework for Event Temporal Relation Extraction

no code implementations • 28 May 2023 • Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao

After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events.

Multi-Label Classification Relation +1

Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED

1 code implementation • ACL 2022 • Quzhe Huang, Shibo Hao, Yuan Ye, Shengqi Zhu, Yansong Feng, Dongyan Zhao

DocRED is a widely used dataset for document-level relation extraction.

Document-level Relation Extraction Relation

Exploring Distantly-Labeled Rationales in Neural Network Models

no code implementations • ACL 2021 • Quzhe Huang, Shengqi Zhu, Yansong Feng, Dongyan Zhao

Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales.

Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction

1 code implementation • ACL 2021 • Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, Dongyan Zhao

Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences.

Document-level Relation Extraction Relation +1