AI Paper Atlas

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

Explicit Interaction Model towards Text Classification

Cunxiao Du, Zhaozheng Chen, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining

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 explicit word-class interaction to the encoder-only model (ablation)EXAM · Amazon Review Polarityaccuracy: 95.1 -> 95.5Improved
Add explicit word-class interaction to the encoder-only model (ablation)EXAM · Amazon Review Fullaccuracy: 60.9 -> 61.9Improved
Add explicit word-class interaction to the encoder-only model (ablation)EXAM · AG's Newsaccuracy: 92.8 -> 93.0Improved
Add explicit word-class interaction to the encoder-only model (ablation)EXAM · Yahoo! Answersaccuracy: 73.1 -> 74.8Improved
Add explicit word-class interaction to the encoder-only model (ablation)EXAM · DBPediaaccuracy: 98.9 -> 99.0Improved
Use EXAM's explicit word-class interactions instead of the strongest reported baselineEXAM · Amazon Review Polarityaccuracy: 95.7 -> 95.5Hurt
Use EXAM's explicit word-class interactions instead of the strongest reported baselineEXAM · Amazon Review Fullaccuracy: 63.0 -> 61.9Hurt
Use EXAM's explicit word-class interactions instead of the strongest reported baselineEXAM · Yahoo! Answersaccuracy: 73.7 -> 74.8Improved
Use EXAM's explicit word-class interactions instead of the strongest reported baselineEXAM · KanShan-CupF1: 0.393 -> 0.397Improved
Use EXAM's explicit word-class interactions instead of the strongest reported baselineEXAM · ZhihuF1: 0.389 -> 0.397Improved

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