Research map / Label-efficient and robust learning / Recognition and long-tail
Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution
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 relation-specific linguistic features (negation, subjectivity, intention, entity continuity) to baseline features | Naive Bayes feature baseline · PDTB Comparison vs other | F1: 38.41 -> 43.24 | Helped |
| add linguistic features | Naive Bayes feature baseline · PDTB Contingency vs other | F1: 53.88 -> 57.82 | Helped |
| add linguistic features | Naive Bayes feature baseline · PDTB four-way | F1: 44.93 -> 47.15 | Helped |
| add linguistic features | Naive Bayes feature baseline · PDTB Expansion vs other | F1: 72.22 -> 72.88 | Helped |
| add linguistic features | Naive Bayes feature baseline · PDTB Temporal vs other | F1: 27.46 -> 29.10 | Helped |
| add Negation features (ablation) | All features · PDTB Comparison vs other | F1: -4.68 when removed | Helped |
| add Intention features (ablation) | All features · PDTB Contingency vs other | F1: -2.29 when removed | Helped |
| add Subjective features (ablation) | All features · PDTB Contingency vs other | F1: -1.39 when removed | Helped |
| add Subjective features (ablation) | All features · PDTB Temporal vs other | F1: -1.52 when removed | Helped |
| add Parallel Entity features (ablation) | All features · PDTB Expansion vs other | F1: -0.15 when removed | No clear effect |
| add Narrowing Entity features (ablation) | All features · PDTB Expansion vs other | F1: -0.05 when removed | No clear effect |
| add Negation features (ablation) | All features · PDTB Contingency vs other | F1: 0.0 | No clear effect |
Closest papers by meaning
- Implicit Discourse Relation Classification via Multi-Task Neural Networks (AAAI 2016 · similarity 0.92)
- Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs (AAAI 2026 · similarity 0.91)
- A Label Dependence-Aware Sequence Generation Model for Multi-Level Implicit Discourse Relation Recognition (AAAI 2022 · similarity 0.90)
- Working Memory-Driven Neural Networks with a Novel Knowledge Enhancement Paradigm for Implicit Discourse Relation Recognition (AAAI 2020 · similarity 0.89)
- ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences (ICLR 2025 · similarity 0.83)
- The Structure of Relation Decoding Linear Operators in Large Language Models (NeurIPS 2025 · 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.