AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Jianfeng Gao, Songhao Piao, Ming Zhou, Hsiao-Wuen Hon

ICML 2020 · Large language models › Language, safety and interpretability · approach: Sign and cross-lingual translation · 274 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly train AE and PAR rather than using either objective alone (ablation)UniLMv2 · SQuAD v1.1F1: 91.0 -> 92.0; 90.7 -> 92.0Improved
Jointly train AE and PAR rather than using AR alone (ablation)UniLMv2 · SQuAD v1.1F1: 89.9 -> 92.0Improved
Use PAR rather than AR for pre-training (ablation)UniLMv2 · SST-2accuracy: 92.3 -> 92.5Improved
Add blockwise factorization to AR-only pre-training (ablation)UniLMv2 · SQuAD v1.1F1: 89.9 -> 90.7Improved
Add relative position bias (ablation)UniLMv2 · SQuAD v1.1F1: 91.5 -> 92.0Improved
Add relative position bias (ablation)UniLMv2 · XSumROUGE-1: 43.69 -> 44.00Mixed
Add relative position bias (ablation)UniLMv2 · Question generation, first splitBLEU-4: 24.70 -> 24.43No clear effect
Use UniLMv2 instead of RoBERTa baseSQuAD v1.1 · SQuAD v1.1F1: 90.6 -> 92.0Improved
Use UniLMv2 instead of BART largeXSum · XSumROUGE-1: 45.14 -> 44.00Hurt

Later papers that compared with this method

1 later accepted paper reports UniLM V2 Base++ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy