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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add explicit word-class interaction to the encoder-only model (ablation) | EXAM · Amazon Review Polarity | accuracy: 95.1 -> 95.5 | Improved |
| Add explicit word-class interaction to the encoder-only model (ablation) | EXAM · Amazon Review Full | accuracy: 60.9 -> 61.9 | Improved |
| Add explicit word-class interaction to the encoder-only model (ablation) | EXAM · AG's News | accuracy: 92.8 -> 93.0 | Improved |
| Add explicit word-class interaction to the encoder-only model (ablation) | EXAM · Yahoo! Answers | accuracy: 73.1 -> 74.8 | Improved |
| Add explicit word-class interaction to the encoder-only model (ablation) | EXAM · DBPedia | accuracy: 98.9 -> 99.0 | Improved |
| Use EXAM's explicit word-class interactions instead of the strongest reported baseline | EXAM · Amazon Review Polarity | accuracy: 95.7 -> 95.5 | Hurt |
| Use EXAM's explicit word-class interactions instead of the strongest reported baseline | EXAM · Amazon Review Full | accuracy: 63.0 -> 61.9 | Hurt |
| Use EXAM's explicit word-class interactions instead of the strongest reported baseline | EXAM · Yahoo! Answers | accuracy: 73.7 -> 74.8 | Improved |
| Use EXAM's explicit word-class interactions instead of the strongest reported baseline | EXAM · KanShan-Cup | F1: 0.393 -> 0.397 | Improved |
| Use EXAM's explicit word-class interactions instead of the strongest reported baseline | EXAM · Zhihu | F1: 0.389 -> 0.397 | Improved |
Closest papers by meaning
- Active Discriminative Text Representation Learning (AAAI 2017 · similarity 0.84)
- Description Based Text Classification with Reinforcement Learning (ICML 2020 · similarity 0.83)
- On the Dynamics of Training Attention Models (ICLR 2021 · similarity 0.83)
- Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification (AAAI 2024 · similarity 0.82)
- Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach (AAAI 2024 · similarity 0.82)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.81)
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.
