Papers › SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

12 May 2020ACL 2020 6arXiv:2005.05635archive 2025-07-28

Hao Tian, Can Gao, Xinyan Xiao, Hao liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu

Recently, sentiment analysis has seen remarkable advance with the help of pre-training approaches. However, sentiment knowledge, such as sentiment words and aspect-sentiment pairs, is ignored in the process of pre-training, despite the fact that they are widely used in traditional sentiment analysis approaches. In this paper, we introduce Sentiment Knowledge Enhanced Pre-training (SKEP) in order to learn a unified sentiment representation for multiple sentiment analysis tasks. With the help of automatically-mined knowledge, SKEP conducts sentiment masking and constructs three sentiment knowledge prediction objectives, so as to embed sentiment information at the word, polarity and aspect level into pre-trained sentiment representation. In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair. Experiments on three kinds of sentiment tasks show that SKEP significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets. We release our code at https://github.com/baidu/Senta.

PaperPDFConference PDFCode

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

Code

baidu/Senta officialmentioned in papermentioned on GitHubpytorch report
Mind23-2/MindCode-96 mentioned on GitHubmindspore report
aaronvvv/sentiment_analysis mentioned on GitHubpaddle report
livingbody/paddlenlp_sentiment mentioned on GitHubpaddle 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.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

MUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationSentiment AnalysisStock Market Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stock Market Prediction Astock ERNIE-SKEP Accuray 60.66 #14 of 17 Archive leaderboard report
Stock Market Prediction Astock ERNIE-SKEP F1-score 60.66 #14 of 17 Archive leaderboard report
Stock Market Prediction Astock ERNIE-SKEP Precision 61.85 #14 of 17 Archive leaderboard report
Stock Market Prediction Astock ERNIE-SKEP Recall 60.59 #14 of 17 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

Introduced by this paper: SKEP

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSKEPSoftmaxTransformerWeight DecayWordPiece

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