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

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

29 Jul 2019arXiv:1907.12412archive 2025-07-28

Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Hao Tian, Hua Wu, Haifeng Wang

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

PaddlePaddle/ERNIE officialmentioned in papermentioned on GitHubpaddleSyntology: 1 sample, 0 ran · 1 unverified report
DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc. mentioned on GitHubSyntology: not harvested report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

1 sample harvested: 0 ran · 1 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1unverified

Licence: 1 of the 1 sample is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from PaddlePaddle/ERNIE. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

PaddlePaddle/ERNIE official repository 1 sample, 0 ran · 1 unverified
calc_lm_head_logits ernie/modeling.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · f277229b3bab1f59 · report

Tasks

Chinese Named Entity RecognitionChinese Reading ComprehensionChinese Sentence Pair ClassificationChinese Sentiment AnalysisLinguistic AcceptabilityMulti-Task LearningNamed Entity Recognition (NER)Natural Language InferenceOpen-Domain Question AnsweringQuestion AnsweringSemantic Textual SimilaritySentiment Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA ERNIE 2.0 Large F1 95 #10 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA ERNIE 2.0 Base F1 93.8 #15 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA Dev ERNIE 2.0 Large F1 96.3 #1 of 3 Archive leaderboard report
Chinese Named Entity Recognition MSRA Dev ERNIE 2.0 Base F1 95.2 #2 of 3 Archive leaderboard report
Linguistic Acceptability CoLA ERNIE 2.0 Large Accuracy 63.5% #27 of 43 Archive leaderboard report
Linguistic Acceptability CoLA ERNIE 2.0 Base Accuracy 55.2% #34 of 43 Archive leaderboard report
Natural Language Inference MultiNLI ERNIE 2.0 Large Matched 88.7 #15 of 67 Archive leaderboard report
Natural Language Inference MultiNLI ERNIE 2.0 Large Mismatched 88.8 #15 of 67 Archive leaderboard report
Natural Language Inference MultiNLI ERNIE 2.0 Base Matched 86.1 #28 of 67 Archive leaderboard report
Natural Language Inference MultiNLI ERNIE 2.0 Base Mismatched 85.5 #28 of 67 Archive leaderboard report
Natural Language Inference QNLI ERNIE 2.0 Large Accuracy 94.6% #14 of 43 Archive leaderboard report
Natural Language Inference QNLI ERNIE 2.0 Base Accuracy 92.9% #24 of 43 Archive leaderboard report
Natural Language Inference RTE ERNIE 2.0 Large Accuracy 80.2% #35 of 90 Archive leaderboard report
Natural Language Inference RTE ERNIE 2.0 Base Accuracy 74.8% #45 of 90 Archive leaderboard report
Natural Language Inference WNLI ERNIE 2.0 Large Accuracy 67.8 #19 of 23 Archive leaderboard report
Natural Language Inference XNLI Chinese ERNIE 2.0 Large Accuracy 81 #1 of 3 Archive leaderboard report
Natural Language Inference XNLI Chinese ERNIE 2.0 Base Accuracy 79.7 #2 of 3 Archive leaderboard report
Natural Language Inference XNLI Chinese Dev ERNIE 2.0 Large Accuracy 82.6 #1 of 3 Archive leaderboard report
Natural Language Inference XNLI Chinese Dev ERNIE 2.0 Base Accuracy 81.2 #2 of 3 Archive leaderboard report
Open-Domain Question Answering DuReader ERNIE 2.0 Large EM 64.2 #1 of 2 Archive leaderboard report
Open-Domain Question Answering DuReader ERNIE 2.0 Base EM 61.3 #2 of 2 Archive leaderboard report
Question Answering Quora Question Pairs ERNIE 2.0 Large Accuracy 90.1% #7 of 19 Archive leaderboard report
Question Answering Quora Question Pairs ERNIE 2.0 Base Accuracy 89.8% #10 of 19 Archive leaderboard report
Semantic Textual Similarity MRPC ERNIE 2.0 Large Accuracy 87.4% #28 of 45 Archive leaderboard report
Semantic Textual Similarity MRPC ERNIE 2.0 Base Accuracy 86.1% #34 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark ERNIE 2.0 Large Pearson Correlation 0.912 #12 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark ERNIE 2.0 Base Pearson Correlation 0.876 #23 of 66 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification ERNIE 2.0 Base Accuracy 95 #25 of 87 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutERNIELayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxWeight DecayWordPieceXLNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections