activity
20192021
most citedERNIE: Enhanced Representation through Knowledge Integration

773 citations · 777 across the 2 of their papers we have counts for

collaborators

5 papers

cs.IR20214 cited

Pre-trained Language Model for Web-scale Retrieval in Baidu Search

Yiding Liu, Guan Huang, Jiaxiang Liu +7

Retrieval is a crucial stage in web search that identifies a small set of query-relevant candidates from a billion-scale corpus. Discovering more semantically-related candidates in…

cs.CL2020

ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding

Dongling Xiao, Yu-Kun Li, Han Zhang +4

Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending t…

cs.CL2020

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

Dongling Xiao, Han Zhang, Yukun Li +4

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced mu…

cs.CL2019

ERNIE 2.0: A Continual Pre-training Framework for Language Understanding

Yu Sun, Shuohuan Wang, Yukun Li +4

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 cru…

cs.CL2019773 cited

ERNIE: Enhanced Representation through Knowledge Integration

Yu Sun, Shuohuan Wang, Yukun Li +7

We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration). Inspired by the masking strategy of BER…