mlsanityData to 7 Oct 2026

Diachronic word embeddings and semantic shifts: a survey

arXiv 1806.03537 ↗First posted 9 Jun 2018cs.CLcited by 90

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed a surge of publications aimed at tracing temporal changes in lexical semantics using distributional methods, particularly prediction-based word embedding models. However, this vein of research lacks the cohesion, common terminology and shared practices of more established areas of natural language processing. In this paper, we survey the current state of academic research related to diachronic word embeddings and semantic shifts detection. We start with discussing the notion of semantic shifts, and then continue with an overview of the existing methods for tracing such time-related shifts with word embedding models. We propose several axes along which these methods can be compared, and outline the main challenges before this emerging subfield of NLP, as well as prospects and possible applications.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 14; 2023: 11; 2024: 13; 2025: 8; 2026: 15.

90 papers.

Sort:

By area:

  1. 2021Time Masking for Temporal Language Modelscited by 46
  2. 2021Explaining and Improving BERT Performance on Lexical Semantic Change Detectioncited by 33
  3. 2021Dynamic Language Models for Continuously Evolving Contentcited by 27
  4. 2021Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corporacited by 21
  5. 2022Temporal Attention for Language Modelscited by 21
  6. 2023A Survey on Contextualised Semantic Shift Detectioncited by 21
  7. 2024A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Changecited by 21
  8. 2022Contextualized language models for semantic change detection: lessons learnedcited by 20
  9. 2023Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysiscited by 19
  10. 2021COVID-19 sentiment analysis via deep learning during the rise of novel casescited by 18
  11. 2021A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communicationcited by 18
  12. 2021Statistically significant detection of semantic shifts using contextual word embeddingscited by 14
38 more
  1. 2021Lexical Semantic Change Discoverycited by 13
  2. 2021Three-part diachronic semantic change dataset for Russiancited by 11
  3. 2022HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysiscited by 11
  4. 2022LSCDiscovery: A shared task on semantic change discovery and detection in Spanishcited by 11
  5. 2021Grammatical Profiling for Semantic Change Detectioncited by 10
  6. 2023Can Word Sense Distribution Detect Semantic Changes of Words?cited by 10
  7. 2023Substitution-based Semantic Change Detection using Contextual Embeddingscited by 9
  8. 2022Building for Tomorrow: Assessing the Temporal Persistence of Text Classifierscited by 8
  9. 2022What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig Harriscited by 8
  10. 2023Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddingscited by 8
  11. 2023Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Modelscited by 8
  12. 2022NorDiaChange: Diachronic Semantic Change Dataset for Norwegiancited by 7
  13. 2024(Chat)GPT v BERT: Dawn of Justice for Semantic Change Detectioncited by 7
  14. 2024Time Machine GPTcited by 7
  15. 2021Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspaperscited by 6
  16. 2023textitSwap and Predict -- Predicting the Semantic Changes in Words across Corpora by Context Swappingcited by 6
  17. 2021Theoretical foundations and limits of word embeddings: what types of meaning can they capture?cited by 5
  18. 2024Survey in Characterizing Semantic Changecited by 5
  19. 2024A Semantic Distance Metric Learning approach for Lexical Semantic Change Detectioncited by 5
  20. 2021Lexical semantic change for Ancient Greek and Latincited by 4
  21. 2021Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detectioncited by 4
  22. 2021Semantic Journeys: Quantifying Change in Emoji Meaning from 2012-2018cited by 4
  23. 2021DRIFT: A Toolkit for Diachronic Analysis of Scientific Literaturecited by 4
  24. 2021Capturing Stance Dynamics in Social Media: Open Challenges and Research Directionscited by 4
  25. 2022A Greek Parliament Proceedings Dataset for Computational Linguistics and Political Analysiscited by 4
  26. 2023Measuring Intersectional Biases in Historical Documentscited by 4
  27. 2025SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detectioncited by 4
  28. 2022Letters From the Past: Modeling Historical Sound Change Through Diachronic Character Embeddingscited by 3
  29. 2022The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemiccited by 3
  30. 2024A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applicationscited by 3
  31. 2024AXOLOTL'24 Shared Task on Multilingual Explainable Semantic Change Modelingcited by 3
  32. 2025Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matricescited by 3
  33. 2026Transparent Semantic Change Detection with Dependency-Based Profilescited by 3
  34. 2021The challenges of temporal alignment on Twitter during crisescited by 2
  35. 2021A Survey On Neural Word Embeddingscited by 2
  36. 2022ImmunoLingo: Linguistics-based formalization of the antibody languagecited by 2
  37. 2023Same Words, Different Meanings: Semantic Polarization in Broadcast Media Language Forecasts Polarization on Social Media Discoursecited by 2
  38. 2023Computational modeling of semantic changecited by 2

50 most cited of 90 All 90 (JSON)