AI Paper Atlas

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

Contrast and Generation Make BART a Good Dialogue Emotion Recognizer

Shimin Li, Hang Yan, Xipeng Qiu

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 122 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
Add response generation as an auxiliary task (ablation)CoG-BART · MELDWeighted-Avg-F1: 64.26 -> 64.81Improved
Add response generation as an auxiliary task (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 64.74 -> 66.18Improved
Add supervised contrastive loss (ablation)CoG-BART · MELDWeighted-Avg-F1: 64.28 -> 64.81Improved
Add supervised contrastive loss (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 64.23 -> 66.18Improved
Prepend speaker labels to utterances (ablation)CoG-BART · MELDWeighted-Avg-F1: 64.14 -> 64.81Improved
Prepend speaker labels to utterances (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 55.41 -> 66.18Improved
Add both response generation and supervised contrastive loss (ablation)CoG-BART · MELDWeighted-Avg-F1: 63.57 -> 64.81Improved
Add both response generation and supervised contrastive loss (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 62.90 -> 66.18Improved
Add supervised contrastive loss and speaker label prepending (ablation)CoG-BART · MELDWeighted-Avg-F1: 63.72 -> 64.81Improved
Add supervised contrastive loss and speaker label prepending (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 54.83 -> 66.18Improved
Add response generation and speaker label prepending (ablation)CoG-BART · MELDWeighted-Avg-F1: 64.02 -> 64.81Improved
Add response generation and speaker label prepending (ablation)CoG-BART · IEMOCAPWeighted-Avg-F1: 54.95 -> 66.18Improved

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