Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

21 Oct 2020 Wenxuan Zhou Kevin Huang Tengyu Ma Jing Huang

Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with multiple possible relations... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Relation Extraction DocRED ATLOP-RoBERTa-large F1 63.40 # 1
Ign F1 61.39 # 1
Relation Extraction DocRED ATLOP-BERT-base F1 61.30 # 4
Ign F1 59.31 # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet