ERNIE: Enhanced Language Representation with Informative Entities

ACL 2019 Zhengyan ZhangXu HanZhiyuan LiuXin JiangMaosong SunQun Liu

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Linguistic Acceptability CoLA ERNIE Accuracy 52.3% # 13
Relation Extraction FewRel ERNIE F1 88.32 # 1
Precision 88.49 # 1
Recall 88.44 # 1
Entity Linking FIGER ERNIE Accuracy 57.19 # 1
Macro F1 76.51 # 1
Micro F1 73.39 # 1
Semantic Textual Similarity MRPC ERNIE Accuracy 88.2% # 11
Natural Language Inference MultiNLI ERNIE Matched 84.0 # 12
Mismatched 83.2 # 9
Entity Typing Open Entity ERNIE F1 75.56 # 1
Precision 78.42 # 1
Recall 72.9 # 1
Natural Language Inference QNLI ERNIE Accuracy 91.3% # 13
Paraphrase Identification Quora Question Pairs ERNIE F1 71.2 # 4
Natural Language Inference RTE ERNIE Accuracy 68.8% # 16
Sentiment Analysis SST-2 Binary classification ERNIE Accuracy 93.5 # 12
Semantic Textual Similarity STS Benchmark ERNIE Pearson Correlation 0.832 # 13
Relation Extraction TACRED ERNIE F1 67.97 # 5
Precision 69.97 # 2
Recall 66.08 # 2

Methods used in the Paper