Research map / Large language models / Language, safety and interpretability
Neural Models for Sequence Chunking
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 pointer-network segmentation instead of IOB-based segmentation | Neural sequence chunking on CoNLL 2000 · CoNLL 2000 | F1: 94.13 -> 94.72 | Helped |
| Use pointer-network segmentation instead of IOB-based segmentation | Neural sequence chunking on CoNLL 2000 · CoNLL 2000 | Segment-F1: 95.28 -> 95.75 | Helped |
| Use IOB-based segmentation with a single Bi-LSTM (Model I) | Neural sequence chunking · CoNLL 2000 | F1: 94.13 -> 94.01 | No clear effect |
| Use IOB-based segmentation with an encoder-decoder (Model II) | Neural sequence chunking · CoNLL 2000 | F1: 94.13 -> 94.13 | No clear effect |
| Use pointer-network segmentation instead of IOB-based segmentation | Slot filling · ATIS | F1: 95.23 -> 95.86 | Helped |
| Use pointer-network segmentation instead of IOB-based segmentation | Slot filling · ATIS | Segment-F1: 98.85 -> 99.01 | Helped |
| Use pointer-network segmentation instead of IOB-based segmentation | Slot filling · LARGE | F1: 75.73 -> 78.49 | Helped |
| Use pointer-network segmentation instead of IOB-based segmentation | Slot filling · LARGE | Segment-F1: 80.79 -> 82.44 | Helped |
| Use IOB-based segmentation with Models I or II rather than the baseline | Slot filling on LARGE · LARGE | Segment-F1: 80.79 -> 79.93; 80.79 -> 79.99 | Hurt |
| Use the encoder-decoder architecture (Model II) rather than Model I | Slot filling · ATIS | F1: 95.25 -> 95.71 | Helped |
| Use the encoder-decoder architecture (Model II) rather than Model I | Slot filling · LARGE | F1: 76.68 -> 77.26 | Helped |
| Use IOB-based segmentation (Models I and II) rather than the baseline | Text chunking · CoNLL 2000 | F1: 94.13 -> 94.01; 94.13 -> 94.13 | No clear effect |
Closest papers by meaning
- Empower Sequence Labeling with Task-Aware Neural Language Model (AAAI 2018 · similarity 0.87)
- Concept-Guided Interpretability via Neural Chunking (NeurIPS 2025 · similarity 0.87)
- Dynamic Chunking for End-to-End Hierarchical Sequence Modeling (ICLR 2026 · similarity 0.86)
- Structured Neural Summarization (ICLR 2019 · similarity 0.86)
- Chunk-Distilled Language Modeling (ICLR 2025 · similarity 0.85)
- RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling (NeurIPS 2025 · similarity 0.85)
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.