Research map / Label-efficient and robust learning / Recognition and long-tail
Syntax-Aware Neural Semantic Role Labeling
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 |
|---|---|---|---|
| Add dependency-tree syntax representations using SDP | Baseline SRL model · CoNLL-2005 Combined | F1: 84.8 -> 85.5 | Helped |
| Add tree-based position features | Baseline SRL model · CoNLL-2005 Combined | F1: 84.8 -> 85.6 | Helped |
| Add pattern embeddings | Baseline SRL model · CoNLL-2005 Combined | F1: 84.8 -> 85.1 | Helped |
| Add predicate-independent Tree-GRU representations | Baseline SRL model with ELMo · CoNLL-2005 WSJ Test | F1: 86.3 -> 86.2 | Hurt |
| Add predicate-independent Tree-GRU representations | Baseline SRL model with ELMo · CoNLL-2005 Combined | F1: 84.8 -> 84.9; p > 0.05 | No clear effect |
| Add the four syntax-aware models as an ensemble instead of using the five-model TPF ensemble | SRL ensemble with ELMo · CoNLL-2005 Combined | F1: 86.0 -> 86.6; 0.6 | Helped |
| Use gold-standard dependency trees instead of automatic parses | TPF · CoNLL-2005 Combined | F1: 81.6 -> 88.3; 6.7 | Helped |
| Use gold-standard dependency trees instead of automatic parses | TPF + ELMo · CoNLL-2005 Combined | F1: 84.8 -> 89.9; 5.1 | Helped |
| Add syntax-aware representations | SRL models · Long-distance arguments in CoNLL-2005 | F1 | Helped |
| Add syntax-aware representations | SRL models · CoNLL-2005 Combined | F1: 0.6 ~ 1.0 | Helped |
Closest papers by meaning
- Deep Semantic Role Labeling With Self-Attention (AAAI 2018 · similarity 0.93)
- Encoder-Decoder Based Unified Semantic Role Labeling with Label-Aware Syntax (AAAI 2021 · similarity 0.91)
- End-to-end Semantic Role Labeling with Neural Transition-based Model (AAAI 2021 · similarity 0.89)
- Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields (AAAI 2024 · similarity 0.88)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.84)
- Short-Context Dominance: How Much Local Context Natural Language Actually Needs? (NeurIPS 2026 · 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.