AI Paper Atlas

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

Latent Emotion Memory for Multi-Label Emotion Classification

Hao Fei, Yue Zhang, Yafeng Ren, Donghong Ji

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 145 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 latent emotion distribution representation to BiGRU features (ablation)LEM · Ren-CECpsmaF1: 0.413 -> 0.448Improved
add latent emotion distribution representation to BiGRU features (ablation)LEM · SemEval2018AP: 0.527 -> 0.568Improved
feed latent emotion representation into memory module (ablation)LEM · Ren-CECpsAP: 0.735 -> 0.751Improved
feed latent emotion representation into memory module (ablation)LEM · SemEval2018maF1: 0.534 -> 0.567Improved
LEM vs RERcmulti-label emotion classifier · Ren-CECpsmiF1: 0.511 vs 0.501Hurt
LEM vs DATNmulti-label emotion classifier · Ren-CECpsAP: 0.732 -> 0.751Improved
increase memory hops beyond best (2 on Ren-CECps, 3 on SemEval) (ablation)LEM · Ren-CECpsF1: 0.448 -> 0.431 (5 hops)Hurt
use 2 memory hops instead of 1 (ablation)LEM · Ren-CECpsF1: 0.434 -> 0.448Improved

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