mlsanityData to 14 Oct 2026

Word Sense Detection Leveraging Maximum Mean Discrepancy

arXiv 2506.01602 ↗First posted 2 Jun 2025cs.CL cs.LG stat.MLcited by 0

Not on the map. Why?

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.

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

12 of 30 references.

References · 12

  1. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  2. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  3. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  4. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  5. 2022TimeLMs: Diachronic Language Models from Twittercited by 131
  6. 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 100
  7. 2018Diachronic word embeddings and semantic shifts: a surveycited by 92
  8. 2023A Survey on Contextualised Semantic Shift Detectioncited by 22
  9. 2023Variable Selection for Kernel Two-Sample Testscited by 7
  10. 2023Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparisoncited by 5
  11. 2024A Semantic Distance Metric Learning approach for Lexical Semantic Change Detectioncited by 5
  12. 2025Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matricescited by 3

Built on by

Not cited yet.