提出新度量方法，提升多语言语义演变检测的准确性与鲁棒性。
Rethinking Metrics for Lexical Semantic Change Detection
- 引入平均最小距离（AMD）和对称平均最小距离（SAMD）衡量词义变化
- AMD在降维和通用编码器下表现更稳定，SAMD在专用编码器中更优
- 挑战传统度量，为语义演变研究提供更可靠的评估工具
词汇语义演变检测（LSCD）越来越多依赖上下文语言模型嵌入，但多数方法仍仅使用少量语义变化度量，主要是平均成对距离（APD）和词原型的余弦距离（PRT）。本文提出新的度量方法：平均最小距离（AMD）和对称平均最小距离（SAMD），通过跨时间周期词用法间的局部对应关系量化语义变化。在多种语言、编码器和表示空间下，我们发现AMD在降维和非专业化编码器条件下表现更稳健，而SAMD在专业化编码器中更优。结果表明，LSCD可从超越APD和PRT的替代度量中获益，其中AMD为基于上下文嵌入的分析提供了稳健选择。
原文摘要 · Abstract (English)
Lexical semantic change detection (LSCD) increasingly relies on contextualised language model embeddings, yet most approaches still quantify change using a small set of semantic change metrics, primarily Average Pairwise Distance (APD) and cosine distance over word prototypes (PRT). We introduce Average Minimum Distance (AMD) and Symmetric Average Minimum Distance (SAMD), new measures that quantify semantic change via local correspondence between word usages across time periods. Across multiple languages, encoder models, and representation spaces, we show that AMD often provides more robust performance, particularly under dimensionality reduction and with non-specialised encoders, while SAMD excels with specialised encoders. We suggest that LSCD may benefit from considering alternative semantic change metrics beyond APD and PRT, with AMD offering a robust option for contextualised embedding-based analysis.
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。