# Rethinking Metrics for Lexical Semantic Change Detection

arXiv: https://arxiv.org/abs/2602.15716 · HTML: https://mlsanity.com/paper/2602.15716/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Analysing Lexical Semantic Change with Contextualised Word Representations](https://mlsanity.com/paper/2004.14118/) (2020)
- [Spanish Pre-trained BERT Model and Evaluation Data](https://mlsanity.com/paper/2308.02976/) (2023)
- [Cultural Shift or Linguistic Drift? Comparing Two Computational Measures of Semantic Change](https://mlsanity.com/paper/1606.02821/) (2016)
- [Temporal Analysis of Language through Neural Language Models](https://mlsanity.com/paper/1405.3515/) (2014)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [mmBERT: A Modern Multilingual Encoder with Annealed Language Learning](https://mlsanity.com/paper/2509.06888/) (2025)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift](https://mlsanity.com/paper/1912.01072/) (2019)
- [Playing with Words at the National Library of Sweden -- Making a Swedish BERT](https://mlsanity.com/paper/2007.01658/) (2020)
- [Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change](https://mlsanity.com/paper/1906.01688/) (2019)
- [UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection](https://mlsanity.com/paper/2005.00050/) (2020)
- [A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains](https://mlsanity.com/paper/1906.02979/) (2019)
- [Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model](https://mlsanity.com/paper/2104.09617/) (2021)
- [A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change](https://mlsanity.com/paper/2402.12011/) (2024)
- [Contextualized language models for semantic change detection: lessons learned](https://mlsanity.com/paper/2209.00154/) (2022)
- [Lexical Semantic Change Discovery](https://mlsanity.com/paper/2106.03111/) (2021)
- [Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types](https://mlsanity.com/paper/2406.03452/) (2024)
- [NorDiaChange: Diachronic Semantic Change Dataset for Norwegian](https://mlsanity.com/paper/2201.05123/) (2022)
- [Definition generation for lexical semantic change detection](https://mlsanity.com/paper/2406.14167/) (2024)
- [SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods](https://mlsanity.com/paper/2505.23714/) (2025)
- [SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection](https://mlsanity.com/paper/2509.11818/) (2025)
- [The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks](https://mlsanity.com/paper/2404.00176/) (2024)

## Abstract (arXiv)

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.