Improving Relation Extraction by Pre-trained Language Representations

Current state-of-the-art relation extraction methods typically rely on a set of lexical, syntactic, and semantic features, explicitly computed in a pre-processing step. Training feature extraction models requires additional annotated language resources, which severely restricts the applicability and portability of relation extraction to novel languages... (read more)

PDF Abstract Automated Knowledge Base Construction Conference 2019 PDF Automated Knowledge Base Construction Conference 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Relation Extraction SemEval-2010 Task 8 TRE F1 87.1 # 12
F1 87:1 # 14
Relation Extraction TACRED TRE F1 67.4 # 15
Relation Extraction TACRED Alt et al. (2019) F1 67.4 # 15

Methods used in the Paper