Neural Metric Learning for Fast End-to-End Relation Extraction

17 May 2019Tung TranRamakanth Kavuluru

Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Relation Extraction ADE Corpus Relation-Metric Entity+Relation F1 77.19 # 2
Entity F1 87.02 # 2
Relation Extraction CoNLL04 Relation-Metric with AT Entity F1 84.15 # 5
Relation F1 62.29 # 4
Relation F1 62.29 # 5

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