通过排序合并语义轴，实现可解释的语义变化检测
SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
- 按语义相似性和贡献度排序并合并嵌入轴
- 保持高检测性能的同时提升可解释性
- 适合需要理解语义演变的研究者
在语义变化检测（SCD）中，如何获得既可解释又高性能的嵌入表示是一个常见难题。通常提升可解释性会牺牲检测性能，反之亦然。为此，我们提出SCDTour，通过排序和合并可解释的语义轴来缓解性能下降问题。SCDTour同时考虑嵌入空间中各轴之间的语义相似性以及每个轴对语义变化的贡献程度。实验表明，SCDTour在保持高可解释性的同时维持了良好的语义变化检测性能。此外，对排序后的轴进行聚合可生成更精细的词义集合，在SCD任务上表现与原始全维嵌入相当或更优。这些结果证明，SCDTour能有效平衡可解释性与性能，使语义变迁可通过少量优化后的轴进行有意义解读。源代码已公开于 https://github.com/LivNLP/svp-tour。
原文摘要 · Abstract (English)
In Semantic Change Detection (SCD), it is a common problem to obtain embeddings that are both interpretable and high-performing. However, improving interpretability often leads to a loss in the SCD performance, and vice versa. To address this problem, we propose SCDTour, a method that orders and merges interpretable axes to alleviate the performance degradation of SCD. SCDTour considers both (a) semantic similarity between axes in the embedding space, as well as (b) the degree to which each axis contributes to semantic change. Experimental results show that SCDTour preserves performance in semantic change detection while maintaining high interpretability. Moreover, agglomerating the sorted axes produces a more refined set of word senses, which achieves comparable or improved performance against the original full-dimensional embeddings in the SCD task. These findings demonstrate that SCDTour effectively balances interpretability and SCD performance, enabling meaningful interpretation of semantic shifts through a small number of refined axes. Source code is available at https://github.com/LivNLP/svp-tour .
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。