Research map / Architectures and efficiency / RNNs and normalization
Automatic Rule Extraction from Long Short Term Memory Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use additive cell decomposition scores instead of cell-difference scores (ablation) | Pattern Matching · Yelp Polarity | accuracy: 81.2 -> 86.5 | Helped |
| Use additive cell decomposition scores instead of gradient scores (ablation) | Pattern Matching · Yelp Polarity | accuracy: 65.0 -> 86.5 | Helped |
| Use additive cell decomposition scores instead of cell-difference scores (ablation) | Pattern Matching · Stanford Sentiment Treebank | accuracy: 77.4 -> 76.2 | Hurt |
| Use additive cell decomposition scores instead of gradient scores (ablation) | Pattern Matching · Stanford Sentiment Treebank | accuracy: 68.0 -> 76.2 | Helped |
| Use additive cell decomposition scores instead of cell-difference scores (ablation) | Pattern Matching · WikiMovies | hits@1 accuracy: 69.4 -> 74.3 | Helped |
| Use additive cell decomposition scores instead of gradient scores (ablation) | Pattern Matching · WikiMovies | hits@1 accuracy: 57.4 -> 74.3 | Helped |
| Replace pattern matching with an LSTM | WikiMovies · WikiMovies | hits@1 accuracy: 74.3 -> 80.1 | Helped |
Closest papers by meaning
- Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM (AAAI 2018 · similarity 0.87)
- Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (AAAI 2019 · similarity 0.86)
- Knowledge-aware Leap-LSTM: Integrating Prior Knowledge into Leap-LSTM towards Faster Long Text Classification (AAAI 2021 · similarity 0.86)
- Mogrifier LSTM (ICLR 2020 · similarity 0.85)
- Extended LSTMs for Knowledge Tracing: Peeking Inside the Black Box (Student Abstract) (AAAI 2025 · similarity 0.85)
- Unlocking the Power of LSTM for Long Term Time Series Forecasting (AAAI 2025 · similarity 0.84)
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.