F1: 89.45
Papers with Code · CC BY-SA 4.0
Relation Extraction
Relation Extraction is the task of predicting attributes and relations for entities in a sentence. For example, given a sentence “Barack Obama was born in Honolulu, Hawaii.”, a relation classifier aims at predicting the relation of “bornInCity”. Relation Extraction is the key component for building relation knowledge graphs, and it is of crucial significance to natural language processing applications such as structured search, sentiment analysis, question answering, and summarization.
<span class="description-source">Source: Deep Residual Learning for Weakly-Supervised Relation Extraction </span>
논문
Relation F1: 68.2
F1: 90.81
NER Micro F1: 89.7RE+ Micro F1: 68.2Sentence Encoder: ALBERTCross Sentence: No
NER Micro F1: 89.0RE+ Micro F1: 66.8Sentence Encoder: ALBERTCross Sentence: No
Relation classification F1: 64.2Cross Sentence: No
NER Micro F1: 85.5RE+ Micro F1: 62.1Sentence Encoder: BERT baseCross Sentence: No
F1: 77.01
Relation classification F1: 67.7Cross Sentence: No
Macro F1: 69.1
Micro F1: 82.34
Relation classification F1: 80.8Cross Sentence: No
NER Micro F1: 83.6RE+ Micro F1: 57.5Sentence Encoder: biLSTMCross Sentence: No
NER Micro F1: 83.4RE+ Micro F1: 55.6Sentence Encoder: biLSTMCross Sentence: No
NER Micro F1: 84.8RE+ Micro F1: 60.2Sentence Encoder: BERT baseCross Sentence: No
NER Micro F1: 83.6RE+ Micro F1: 59.6Sentence Encoder: biLSTMCross Sentence: No
Relation classification F1: 58.2Cross Sentence: No
F1: 84.3
NER Micro F1: 84.2RE+ Micro F1: 59.1Sentence Encoder: biLSTMCross Sentence: No
F1: 42.83
F1: 70.57
F1: 80.35
Micro F1: 84.90F1: 84.90
F1: 88.46
F1: 79.20
Relation classification F1: 80.5Cross Sentence: No
Relation classification F1: 61.3Cross Sentence: No
NER Micro F1: 85.98Sentence Encoder: ELMoCross Sentence: No