Research map / Large language models / Language, safety and interpretability
Exploring the Terrain of Metaphor Novelty: A Regression-Based Approach for Automatically Scoring Metaphors
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 syntax/positional (SynPos) features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.3595 -> 0.4600 | Helped |
| add word embedding features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.3779 -> 0.4600 | Helped |
| add concreteness features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4597 -> 0.4600 | No clear effect |
| add imageability features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4568 -> 0.4600 | No clear effect |
| add sentiment features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4581 -> 0.4600 | No clear effect |
| add ambiguity features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4551 -> 0.4600 | No clear effect |
| add co-occurrence (PMI) features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4530 -> 0.4600 | No clear effect |
| add topic model features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4563 -> 0.4600 | No clear effect |
| add WordNet synset features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.4579 -> 0.4600 | No clear effect |
| add embeddings to SynPos features (ablation) | DNN metaphor novelty scorer · Metaphor novelty test set (3162 word pairs) | r: 0.3566 -> 0.4523 | Helped |
| use novelty regression instead of adapted metaphor detection (Tsvetkov et al.) (ablation) | Metaphor novelty regression approach · Adjective-noun pairs subset | r: 0.2716 -> 0.4483 | Helped |
Closest papers by meaning
- Explainable Metaphor Identification Inspired by Conceptual Metaphor Theory (AAAI 2022 · similarity 0.86)
- CAMEL: Capturing Metaphorical Alignment with Context Disentangling for Multimodal Emotion Recognition (AAAI 2024 · similarity 0.81)
- AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text (ICLR 2025 · similarity 0.81)
- ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences (ICLR 2025 · similarity 0.80)
- Metaphor Is Not All Attention Needs (NeurIPS 2026 · similarity 0.80)
- Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension (AAAI 2024 · similarity 0.80)
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.