Research map / Graph learning / GNN architectures
Contextualized Non-Local Neural Networks for Sequence Learning
Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi Kit Cheung
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 dependency edge attributes to CN³ LSTM (ablation) | CN³ LSTM · QC | score: 94.2 -> 95.0 | Improved |
| Add dependency edge attributes to CN³ LSTM (ablation) | CN³ LSTM · SUBJ | score: 93.5 -> 94.6 | Improved |
| Add dependency edge attributes to CN³ LSTM (ablation) | CN³ LSTM · SICK | score: 80.2 -> 81.9 | Improved |
| Add dependency edge attributes to CN³ LSTM (ablation) | CN³ LSTM · SNLI | score: 81.3 -> 83.5 | Improved |
| Add character features to CN³ LSTM (ablation) | CN³ LSTM · MR | score: 81.3 -> 82.5 | Improved |
| Add character features to CN³ LSTM (ablation) | CN³ LSTM · IMDB | score: 91.5 -> 92.5 | Improved |
| Add character features to CN³ LSTM (ablation) | CN³ LSTM · SST | score: 87.5 -> 88.0 | Improved |
| Add character features to CN³ LSTM (ablation) | CN³ LSTM · QC | score: 94.2 -> 94.6 | Improved |
| Add character features to CN³ LSTM (ablation) | CN³ LSTM · SUBJ | score: 93.5 -> 94.0 | Improved |
| Add character and spelling features to CN³ LSTM (ablation) | CN³ LSTM · POS | score: 97.12 -> 97.78 | Improved |
| Add character and spelling features to CN³ LSTM (ablation) | CN³ LSTM · Chunking | score: 93.81 -> 95.13 | Improved |
| Add character and spelling features to CN³ LSTM (ablation) | CN³ LSTM · NER | score: 89.33 -> 91.10 | Improved |
Closest papers by meaning
- Learning Sequence Representations by Non-local Recurrent Neural Memory (IJCV 2022 · similarity 0.87)
- Empower Sequence Labeling with Task-Aware Neural Language Model (AAAI 2018 · similarity 0.86)
- Non-Local Recurrent Neural Memory for Supervised Sequence Modeling (ICCV 2019 · similarity 0.86)
- Sequence-to-Sequence Learning with Latent Neural Grammars (NeurIPS 2021 · similarity 0.86)
- The Missing Alignment Link of In-context Learning on Sequences (ICML 2025 · similarity 0.84)
- In-Context Language Learning: Architectures and Algorithms (ICML 2024 · 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.
