# Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes

arXiv: https://arxiv.org/abs/2407.02820 · HTML: https://mlsanity.com/paper/2407.02820/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Evaluating the Underlying Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.08783/) (2019)
- [Statistically Significant Detection of Linguistic Change](https://mlsanity.com/paper/1411.3315/) (2014)
- [Survey of Computational Approaches to Lexical Semantic Change](https://mlsanity.com/paper/1811.06278/) (2018)
- [Temporal Analysis of Language through Neural Language Models](https://mlsanity.com/paper/1405.3515/) (2014)
- [Time Masking for Temporal Language Models](https://mlsanity.com/paper/2110.06366/) (2021)
- [XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization](https://mlsanity.com/paper/2010.06478/) (2020)
- [Dynamic Word Embeddings for Evolving Semantic Discovery](https://mlsanity.com/paper/1703.00607/) (2017)
- [Explaining and Improving BERT Performance on Lexical Semantic Change Detection](https://mlsanity.com/paper/2103.07259/) (2021)
- [UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection](https://mlsanity.com/paper/2005.00050/) (2020)
- [A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change](https://mlsanity.com/paper/2402.12011/) (2024)
- [Discovering Universal Geometry in Embeddings with ICA](https://mlsanity.com/paper/2305.13175/) (2023)
- [AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples](https://mlsanity.com/paper/2104.08639/) (2021)
- [Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings](https://mlsanity.com/paper/2305.08654/) (2023)
- [Definition generation for lexical semantic change detection](https://mlsanity.com/paper/2406.14167/) (2024)
- [textitSwap and Predict -- Predicting the Semantic Changes in Words across Corpora by Context Swapping](https://mlsanity.com/paper/2310.10397/) (2023)
- [A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection](https://mlsanity.com/paper/2403.00226/) (2024)
- [Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation](https://mlsanity.com/paper/2208.10734/) (2022)

## Built on by (most cited first, 4 of 4)

- [SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection](https://mlsanity.com/paper/2509.11818/) (2025)
- [Improving Interpretability of Lexical Semantic Change with Neurobiological Features](https://mlsanity.com/paper/2602.09760/) (2026)
- [Tracking Temporal Dynamics of Vector Sets with Gaussian Process](https://mlsanity.com/paper/2512.15538/) (2025)
- [Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change](https://mlsanity.com/paper/2609.30974/) (2026)

## Abstract (arXiv)

The sense-aware contextualised word embeddings (SCWEs) encode semantic changes of words within the contextualised word embedding (CWE) spaces. Despite the superior performance of SCWEs in contextual/temporal semantic change detection (SCD) benchmarks, it remains unclear as to how the meaning changes are encoded in the embedding space. To study this, we compare pre-trained CWEs and their fine-tuned versions on contextual and temporal semantic change benchmarks under Principal Component Analysis (PCA) and Independent Component Analysis (ICA) transformations. Our experimental results reveal (a) although there exist a smaller number of axes that are specific to semantic changes of words in the pre-trained CWE space, this information gets distributed across all dimensions when fine-tuned, and (b) in contrast to prior work studying the geometry of CWEs, we find that PCA to better represent semantic changes than ICA within the top 10% of axes. These findings encourage the development of more efficient SCD methods with a small number of SCD-aware dimensions. Source code is available at https://github.com/LivNLP/svp-dims .