Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders

Named entity recognition and relation extraction are two important fundamental problems. Joint learning algorithms have been proposed to solve both tasks simultaneously, and many of them cast the joint task as a table-filling problem... (read more)

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Relation Extraction ACE 2004 Table-Sequence RE Micro F1 63.3 # 1
NER Micro F1 88.6 # 1
RE+ Micro F1 59.6 # 1
Relation Extraction ACE 2005 Table-Sequence RE Micro F1 67.6 # 1
NER Micro F1 89.5 # 1
RE+ Micro F1 64.3 # 1
Sentence Encoder ALBERT # 1
Relation Extraction ADE Corpus Table-Sequence RE+ Macro F1 80.1 # 3
NER Macro F1 89.7 # 1
RE Macro F1 80.1 # 1
Relation Extraction CoNLL04 Table-Sequence NER Macro F1 86.9 # 2
RE+ Micro F1 73.6 # 1
RE+ Macro F1 75.4 # 1
NER Micro F1 90.1 # 1

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