Papers › PERT: Pre-training BERT with Permuted Language Model

PERT: Pre-training BERT with Permuted Language Model

14 Mar 2022arXiv:2203.06906archive 2025-07-28

Yiming Cui, Ziqing Yang, Ting Liu

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for natural language understanding (NLU). PERT is an auto-encoding model (like BERT) trained with Permuted Language Model (PerLM). The formulation of the proposed PerLM is straightforward. We permute a proportion of the input text, and the training objective is to predict the position of the original token. Moreover, we also apply whole word masking and N-gram masking to improve the performance of PERT. We carried out extensive experiments on both Chinese and English NLU benchmarks. The experimental results show that PERT can bring improvements over various comparable baselines on some of the tasks, while others are not. These results indicate that developing more diverse pre-training tasks is possible instead of masked language model variants. Several quantitative studies are carried out to better understand PERT, which might help design PLMs in the future. Resources are available: https://github.com/ymcui/PERT

PaperPDFCode

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

Code

ymcui/pert officialmentioned in papermentioned on GitHubtfApache-2.0 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

Language ModelingLanguage ModellingNatural Language UnderstandingStock Market Predictionmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stock Market Prediction Astock Chinese Pert Large (News+Factors) Accuray 67.37 #4 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News+Factors) F1-score 67.27 #4 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News+Factors) Precision 67.28 #4 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News+Factors) Recall 67.73 #4 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News) Accuray 65.09 #8 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News) F1-score 65.03 #8 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News) Precision 65.02 #8 of 17 Archive leaderboard report
Stock Market Prediction Astock Chinese Pert Large (News) Recall 65.07 #8 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.

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