Research map / Label-efficient and robust learning / Recognition and long-tail
Labeling the Semantic Roles of Commas
Naveen Arivazhagan, Christos Christodoulopoulos, Dan Roth
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 |
|---|---|---|---|
| Remove constituency parse features (ablation) | Learned classifier · Gold-Gold | accuracy (%): 87.1 -> 74.1 | Hurt |
| Remove constituency parse features (ablation) | Learned classifier · Auto-Auto | accuracy (%): 83.6 -> 74.1 | Hurt |
| Remove POS features (ablation) | Learned classifier · Gold-Gold | accuracy (%): 87.1 -> 86.1 | Hurt |
| Remove POS features (ablation) | Learned classifier · Auto-Auto | accuracy (%): 83.6 -> 82.3 | Hurt |
| Remove shallow parse features (ablation) | Learned classifier · Gold-Gold | accuracy (%): 87.1 -> 86.7 | Hurt |
| Remove shallow parse features (ablation) | Learned classifier · Auto-Auto | accuracy (%): 83.6 -> 83.2 | Hurt |
| Remove NER features (ablation) | Learned classifier · Gold-Gold | accuracy (%): 87.1 -> 87.0 | No clear effect |
| Remove NER features (ablation) | Learned classifier · Auto-Auto | accuracy (%): 83.6 -> 83.4 | No clear effect |
| Add NER feature (ablation) | Learned classifier · LOCATIVE label | F1: +0.2 | Improved |
| Learned local classifier vs comma-syntax-pattern baseline | Learned classifier · Auto-Auto | accuracy (%): 80.5 -> 83.6 | Improved |
| Learned local classifier vs comma-syntax-pattern baseline | Learned classifier · Gold-Gold | accuracy (%): 85.3 -> 87.1 | Improved |
| Structured sequential model over all commas in a sentence instead of local classifier | Learned classifier · Gold-Gold | accuracy (%): 87.1 -> 82.1 | Hurt |
Closest papers by meaning
- Syntax-Aware Neural Semantic Role Labeling (AAAI 2019 · similarity 0.84)
- Learning to Map Frequent Phrases to Sub-Structures of Meaning Representation for Neural Semantic Parsing (AAAI 2020 · similarity 0.84)
- Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution (AAAI 2018 · similarity 0.83)
- COMM: Concentrated Margin Maximization for Robust Document-Level Relation Extraction (AAAI 2025 · similarity 0.83)
- Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields (AAAI 2024 · similarity 0.82)
- Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks (AAAI 2024 · similarity 0.82)
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.
