ERNIE: Enhanced Representation through Knowledge Integration

19 Apr 2019Yu SunShuohuan WangYukun LiShikun FengXuyi ChenHan ZhangXin TianDanxiang ZhuHao TianHua Wu

We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration). Inspired by the masking strategy of BERT, ERNIE is designed to learn language representation enhanced by knowledge masking strategies, which includes entity-level masking and phrase-level masking... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Chinese Sentiment Analysis ChnSentiCorp ERNIE Accuracy 95.4 # 3
Chinese Sentiment Analysis ChnSentiCorp Dev ERNIE Accuracy 95.2 # 3
Chinese Sentence Pair Classification LCQMC ERNIE Accuracy 87.4 # 3
Chinese Sentence Pair Classification LCQMC Dev ERNIE Accuracy 89.7 # 2
Chinese Named Entity Recognition MSRA ERNIE F1 93.8 # 8
Chinese Named Entity Recognition MSRA Dev ERNIE F1 95 # 3
Chinese Sentence Pair Classification NLPCC-DBQA ERNIE MRR 95.1 # 3
F1 82.7 # 2
Chinese Sentence Pair Classification NLPCC-DBQA Dev ERNIE MRR 95 # 3
F1 82.3 # 1
Natural Language Inference XNLI Chinese ERNIE Accuracy 78.4 # 3
Natural Language Inference XNLI Chinese Dev ERNIE Accuracy 79.9 # 3

Methods used in the Paper