# Word Sense Detection Leveraging Maximum Mean Discrepancy

arXiv: https://arxiv.org/abs/2506.01602 · HTML: https://mlsanity.com/paper/2506.01602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 12 of 12)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [TimeLMs: Diachronic Language Models from Twitter](https://mlsanity.com/paper/2202.03829/) (2022)
- [Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy](https://mlsanity.com/paper/1611.04488/) (2016)
- [Diachronic word embeddings and semantic shifts: a survey](https://mlsanity.com/paper/1806.03537/) (2018)
- [A Survey on Contextualised Semantic Shift Detection](https://mlsanity.com/paper/2304.01666/) (2023)
- [Variable Selection for Kernel Two-Sample Tests](https://mlsanity.com/paper/2302.07415/) (2023)
- [Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison](https://mlsanity.com/paper/2311.01537/) (2023)
- [A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection](https://mlsanity.com/paper/2403.00226/) (2024)
- [Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices](https://mlsanity.com/paper/2501.09538/) (2025)

## Abstract (arXiv)

Word sense analysis is an essential analysis work for interpreting the linguistic and social backgrounds. The word sense change detection is a task of identifying and interpreting shifts in word meanings over time. This paper proposes MMD-Sense-Analysis, a novel approach that leverages Maximum Mean Discrepancy (MMD) to select semantically meaningful variables and quantify changes across time periods. This method enables both the identification of words undergoing sense shifts and the explanation of their evolution over multiple historical periods. To my knowledge, this is the first application of MMD to word sense change detection. Empirical assessment results demonstrate the effectiveness of the proposed approach.