Research map / Reinforcement learning / Visual and representation RL
Learning Structured Representation for Text Classification via Reinforcement Learning
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 |
|---|---|---|---|
| learn structure with RL (HS-LSTM) vs no structure LSTM | text classification · MR | accuracy: 77.4 -> 82.1 | Helped |
| use RL-discovered phrase structure instead of parser-defined structure (ablation) | hierarchical LSTM · SST-binary | accuracy: 86.5 -> 87.8 | Helped |
| HS-LSTM vs Tree-LSTM | text classification · SST | accuracy: 50.1 -> 49.8 | No clear effect |
Closest papers by meaning
- Modelling Sentence Pairs via Reinforcement Learning: An Actor-Critic Approach to Learn the Irrelevant Words (AAAI 2020 · similarity 0.89)
- Learning to Compose Words into Sentences with Reinforcement Learning (ICLR 2017 · similarity 0.89)
- Description Based Text Classification with Reinforcement Learning (ICML 2020 · similarity 0.87)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.85)
- Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision (NeurIPS 2025 · similarity 0.84)
- Incremental Sequence Classification with Temporal Consistency (NeurIPS 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.