模型靠语境线索泛化，而非死记硬背词汇。
Learning the Cue or Learning the Word? Analyzing Generalization in Metaphor Detection for Verbs
- 用排除法测试模型是否依赖具体词汇，仅靠上下文仍能准确判断隐喻。
- 未见过的动词在上下文中识别率超70%，表明模型学到的是通用模式。
- 适合研究模型泛化机制或提升自然语言理解可解释性的研究者。
隐喻检测模型在基准测试中表现优异，但其性能是否源于可迁移的泛化能力，还是对词汇的机械记忆尚不明确。为此，我们以 RoBERTa 为共享主干，基于阿姆斯特丹大学隐喻语料库（VU Amsterdam Metaphor Corpus）中的英语动词，分析隐喻检测的泛化能力。提出一种受控的词汇隔离设置：所有选定目标词形（lemmas）严格排除在微调数据之外，对比模型在隔离词（Held-out lemmas）与暴露词（Exposed lemmas）上的预测表现。结果显示，尽管模型在暴露词上表现最佳，但在隔离词上仍保持稳健性能。进一步分析发现，仅凭句子上下文即可在隔离词上达到接近全模型的表现，而静态动词级嵌入则无效。结果表明，泛化主要依赖‘学习线索’（可迁移的上下文模式），而‘学习词语’（词形特异性记忆）仅在有词汇暴露时提供额外增益。
原文摘要 · Abstract (English)
Metaphor detection models achieve strong benchmark performance, yet it remains unclear whether this reflects transferable generalization or lexical memorization. To address this, we analyze generalization in metaphor detection through RoBERTa, the shared backbone of many state-of-the-art systems, focusing on English verbs using the VU Amsterdam Metaphor Corpus. We introduce a controlled lexical hold-out setup where all instances of selected target lemmas are strictly excluded from fine-tuning, and compare predictions on these Held-out lemmas against Exposed lemmas (verbs seen during fine-tuning). While the model performs best on Exposed lemmas, it maintains robust performance on Held-out lemmas. Further analysis reveals that sentence context alone is sufficient to match full-model performance on Held-out lemmas, whereas static verb-level embeddings are not. Together, these results suggest that generalization is primarily driven by "learning the cue" (transferable contextual patterns), while "learning the word" (verb-specific memorization) provides an additive boost when lexical exposure is available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。