Research map / Label-efficient and robust learning / Recognition and long-tail
A Generalized Idiom Usage Recognition Model Based on Semantic Compatibility
Changsheng Liu, Rebecca Hwa
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 semantic compatibility layer (ablation) | ACE+LocalAtt+AKEW · SemEval+VNC average | avg figurative F-score: 0.76 -> 0.67 | Hurt |
| Remove semantic compatibility layer (ablation) | ACE+GlobalAtt+AKEW · SemEval+VNC average | avg figurative F-score: 0.74 -> 0.66 | Hurt |
| Remove semantic compatibility layer (ablation) | BiLSTM+GlobalAtt+AKEW · SemEval+VNC average | avg figurative F-score: 0.71 -> 0.65 | Hurt |
| Remove semantic compatibility layer (ablation) | BiLSTM+LocalAtt+AKEW · SemEval+VNC average | avg figurative F-score: 0.73 -> 0.66 | Hurt |
| Remove attention (ablation) | ACE+AKEW · SemEval+VNC average | avg figurative F-score: 0.76 -> 0.66 | Hurt |
| Remove attention (ablation) | BiLSTM+AKEW · SemEval+VNC average | avg figurative F-score: 0.73 -> 0.7 | Hurt |
| Use local attention instead of global attention (ablation) | BiLSTM+AKEW · SemEval+VNC average | avg figurative F-score: 0.71 -> 0.73 | Improved |
| Use BiLSTM instead of ACE without attention (ablation) | AKEW · SemEval+VNC average | avg figurative F-score: 0.66 -> 0.7 | Improved |
| Use BiLSTM instead of ACE with attention (ablation) | LocalAtt+AKEW · SemEval+VNC average | avg figurative F-score: 0.76 -> 0.73 | Hurt |
| Use AKWE instead of AWE for idiom literal representation (ablation) | ACE+LocalAtt · SemEval | avg figurative F-score: 0.74 -> 0.76 | Improved |
| Use AKWE instead of AWE for idiom literal representation (ablation) | ACE+GlobalAtt · SemEval | avg figurative F-score: 0.72 -> 0.74 | Improved |
| Use AKWE instead of AWE (ablation) | ACE+LocalAtt · VNC | avg figurative F-score: 0.76 -> 0.75 | Hurt |
Closest papers by meaning
- Representations of Context in Recognizing the Figurative and Literal Usages of Idioms (AAAI 2017 · similarity 0.94)
- Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension (AAAI 2024 · similarity 0.85)
- Translate Meanings, Not Just Words: IdiomKB’s Role in Optimizing Idiomatic Translation with Language Models (AAAI 2024 · similarity 0.85)
- McHirc: A Multimodal Benchmark for Chinese Idiom Reading Comprehension (AAAI 2025 · similarity 0.82)
- ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences (ICLR 2025 · similarity 0.80)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.79)
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.
