首个可复现的中文隐喻词识别基线，支持多架构对比。
A Reproducible Multi-Architecture Baseline for Token-Level Chinese Metaphor Identification under the MIPVU Framework
- 构建三种模型架构：RoBERTa、MelBERT和Qwen3.5-9B，统一评估框架。
- MelBERT在测试集上达到0.7281的正类F1，优于其他模型。
- 开源全部数据与代码，助力后续中文隐喻研究可复现。
隐喻在日常语言中普遍存在，但基于MIPVU框架的中文词汇级隐喻识别仍远落后于英文。本文提出首个可复现的多架构基线，针对唯一的公开中文MIPVU标注语料库PSU CMC。系统比较三类模型：(i) 基于中文RoBERTa-wwm-ext-large的编码器微调；(ii) 使用新构建的《现代汉语词典》第七版（MCD7）基础义资源（含74,823词条，覆盖PSU CMC词汇71.51%）适配的MelBERT；(iii) 经QLoRA微调的Qwen3.5-9B生成式基线。在五个固定种子下，MelBERT MIP-only取得最高性能，测试正类F1为0.7281±0.0050，略高于MelBERT Full（0.7270±0.0069），显著优于纯RoBERTa（0.7142±0.0121）。Qwen QLoRA配置则落后约11 F1点（0.6157±0.0113）。三个发现值得关注：(1) 中文环境下MelBERT的SPV通道未提供可靠正向信号，反映常规隐喻占主导；(2) 生成式模型差距集中于召回率，体现生成输出离散承诺的局限性；(3) 部分任务设计失败源于格式而非模型能力。论文发布所有划分清单、每种子结果、MCD7基础义嵌入流程及训练脚本，作为未来中文隐喻识别研究的通用参考。
原文摘要 · Abstract (English)
Metaphor is pervasive in everyday language, yet token-level computational identification of metaphor-related words in Chinese under the MIPVU framework remains under-explored relative to English. This paper presents a reproducible multi-architecture baseline for token-level metaphor identification on the PSU Chinese Metaphor Corpus (PSU CMC), the only widely available MIPVU-annotated Chinese corpus. We systematically compare three model families: (i) encoder fine-tuning with Chinese RoBERTa-wwm-ext-large; (ii) MelBERT adapted to Chinese using a newly constructed basic-meaning resource derived from the Modern Chinese Dictionary, 7th edition (MCD7), comprising 74,823 entries with 71.51% PSU CMC vocabulary coverage; and (iii) Qwen3.5-9B fine-tuned with QLoRA as an instruction-tuned generative baseline. Across five fixed seeds, MelBERT MIP-only achieves the strongest performance at 0.7281 +/- 0.0050 test positive F1, marginally above MelBERT Full (0.7270 +/- 0.0069) and clearly above plain RoBERTa (0.7142 +/- 0.0121). The Qwen QLoRA generative configuration trails encoder baselines by approximately 11 F1 points (0.6157 +/- 0.0113). Three findings merit attention: (1) the SPV channel of MelBERT does not contribute reliable positive signal in Chinese, consistent with the dominance of conventional metaphor; (2) the Qwen-encoder gap is concentrated in recall, reflecting the discrete-commitment limitation of generative output; (3) several Qwen task formulations fail due to format design rather than model capacity. We release all split manifests, per-seed outputs, the MCD7 basic-meaning embedding pipeline, and training scripts to serve as a common reference for future Chinese metaphor identification research.
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。