AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Uniform Semantic Features for Natural Language and Programming Language Globally, Locally and Sequentially

Yudong Zhang, Wenhao Zheng, Ming Li

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
remove global information (ablation)UniEmbed · dup-questionAUC: 95.44% -> 60.75%Hurt
remove global information (ablation)UniEmbed · code-cloneAUC: 87.69% -> 50.00%∗Hurt
remove local information (ablation)UniEmbed · dup-questionAUC: 95.44% -> 64.81%Hurt
remove local information (ablation)UniEmbed · code-annoF-measure: 71.85% -> 47.54%Hurt
remove sequential information (ablation)UniEmbed · dup-questionF-measure: 87.70% -> 63.88%Hurt
remove sequential information (ablation)UniEmbed · code-annoAUC: 78.21% -> 49.95%Hurt
remove attention layer (ablation)UniEmbed · dup-questionAUC: 95.44% -> 82.66%Hurt
remove attention layer (ablation)UniEmbed · code-cloneF-measure: 80.31% -> 74.40%Hurt
remove attention layer (ablation)UniEmbed · code-annoAUC: 78.21% -> 65.59%Hurt
joint training on all three datasets instead of single-task trainingUniEmbed · code-cloneAUC: 70.50% -> 87.69%Improved
joint training instead of single-task trainingUniEmbed · dup-questionAUC: 92.64% -> 95.44%Improved
joint training instead of single-task trainingUniEmbed · code-annoAUC: 75.15% -> 78.21%Improved

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