ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing. Current pre-training procedures usually focus on training the model with several simple tasks to grasp the co-occurrence of words or sentences. However, besides co-occurring, there exists other valuable lexical, syntactic and semantic information in training corpora, such as named entity, semantic closeness and discourse relations. In order to extract to the fullest extent, the lexical, syntactic and semantic information from training corpora, we propose a continual pre-training framework named ERNIE 2.0 which builds and learns incrementally pre-training tasks through constant multi-task learning. Experimental results demonstrate that ERNIE 2.0 outperforms BERT and XLNet on 16 tasks including English tasks on GLUE benchmarks and several common tasks in Chinese. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.
PDF AbstractCode
Tasks
Chinese Named Entity Recognition
Chinese Reading Comprehension
Chinese Sentence Pair Classification
Chinese Sentiment Analysis
Linguistic Acceptability
Multi-Task Learning
Named Entity Recognition (NER)
Natural Language Inference
Open-Domain Question Answering
Question Answering
Semantic Textual Similarity
Sentiment Analysis
GLUE
SST
MultiNLI
QNLI
MRPC
CoLA
XNLI
Quora
CMRC
DuReader
Quora Question Pairs
DRCD
