Elamur Research⌕
☰
home / papers / 2026 / Transparent Semantic Change Detection with Dependency-Based Profiles

Transparent Semantic Change Detection with Dependency-Based Profiles

Summary

Neural embedding methods dominate lexical semantic change (LSC) detection, but they offer little insight into why a word is flagged as changed. The authors (KU Leuven and partners) propose a transparent alternative that describes each target word by its syntactic environment. For every dependency relation ("slot"), such as adjectival modifiers or governing verbs, they collect the distribution of lexical fillers in each time period. Corpora are parsed with Stanza, and shifts within each slot are measured with Jensen-Shannon Divergence. Slots above a divergence cutoff are then combined into a word-level change score.

The unsupervised method is evaluated on SemEval 2020 Task 1 (binary Subtask 1 and graded Subtask 2) for English, German, Latin and Swedish. It is competitive and beats several distributional models in some languages and subtasks, though it stays below state-of-the-art systems built on large pretrained models.

Its main value is interpretability. Every prediction can be traced to specific collocates that rose or declined, which makes the method suited to linguistic and humanities research. It can also serve as a check on embedding-based results.

Key points

  • Data: the SemEval 2020 Task 1 benchmark, with two-period diachronic corpora and DURel-based gold labels.
    • Targets per language: English 37, German 48, Latin 40, Swedish 32.
    • Stanza output was aligned with the gold targets by relabelling target POS tags as TAR and normalising spelling variants.
  • Method:
    • JSD is computed per slot over the distribution of fillers (e.g., chi_amod, chi_obj, pa_obj).
    • Only slots with divergence at or above 0.5 enter the aggregate score.
    • Denoising (dropping singleton fillers, stripping POS tags from fillers) proved essential.
  • Interpretable examples:
    • English plane shows its AIRCRAFT sense growing (modifiers like military, japanese) while DIMENSIONAL uses (horizontal, vertical) decline.
    • Latin dolus shows narrowing and pejoration from TRICK to FRAUD in the governing-verb slot (JSD 0.933).
    • Some detected shifts were missing from the gold annotations.
  • Error sources:
    • Real changes are missed when they fall just under the cutoff, e.g., record (set/break a record, JSD 0.48) and Swedish motiv (amod slot, 0.436).
    • Change is overestimated when idioms or highly productive combinations dominate a slot.
    • The method requires a reliable dependency parser, so it does not suit low-resource languages.
  • Resource: all code is released at github.com/phantatbach/LChange26-Dep. Proposed future work includes adaptive slot weighting and hybrid embedding-plus-slot methods.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.lchange-1.8

@inproceedings{tat2026transparent,
  title = {{Transparent Semantic Change Detection with Dependency-Based Profiles}},
  author = {Tat, Bach Phan and Heylen, Kris and Geeraerts, Dirk and Pascale, Stefano De and Speelman, Dirk},
  booktitle = {The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange'26)},
  year = {2026},
  doi = {10.18653/v1/2026.lchange-1.8},
  url = {https://doi.org/10.18653/v1/2026.lchange-1.8}
}

References

59 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josep Alba-Salas. 2007. On the life and death of a collocation: A corpus-based diachronic study of dar miedo/hacer miedo-type structures in Spanish. Diachronica, 24(2):207–252. Publisher: John Benjamins Type: Journal Article. find
  2. Laurence Anthony. 2014. AntConc (Version 3.4. 3)[Computer Software]. Tokyo, Japan: Waseda University. find
  3. Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, Salvador García, Sergio Gil-López, Daniel Molina, Richard Benjamins, Raja Chatila, and Francisco Herrera. 2019. Explainable artificial intelligence (xai): Concepts, taxonomies, opportuni… find
  4. Marco Baroni, Georgiana Dinu, and Germán Kruszewski. 2014. Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 238–247, Bal… find our card
  5. Marco Baroni and Alessandro Lenci. 2010. Distributional memory: A general framework for corpus-based semantics. Computational Linguistics, 36(4):673–721. find our card
  6. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5:135–146. Place: Cambridge, MA Publisher: MIT Press. find
  7. Vaclav Brezina, Pauline Weill-Tessier, and Tony McEnery. 2021. \#lancsbox v. 6.x. Lancaster University. Software version 6.x. find
  8. John A. Bullinaria and Joseph P. Levy. 2007. Extracting semantic representations from word co-occurrence statistics: A computational study. Behavior Research Methods, 39(3):510–526. find
  9. Pierluigi Cassotti, Lucia Siciliani, Marco DeGemmis, Giovanni Semeraro, and Pierpaolo Basile. 2023. XL-LEXEME: WiC Pretrained Model for Cross-Lingual LEXical sEMantic changE. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 15… find
  10. Kenneth Ward Church and Patrick Hanks. 1990. Word Association Norms, Mutual Information, and Lexicography. Computational Linguistics, 16(1):22–29. find our card
  11. Thomai Dalpanagioti. 2019. From corpus usages to cognitively informed dictionary senses. Lexicography, 6(2):75–104. find
  12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  13. Ted Dunning. 1993. Accurate Methods for the Statistics of Surprise and Coincidence. Computational Linguistics, 19(1):61–74. Place: Cambridge, MA Publisher: MIT Press. find our card
  14. Stephanie Evert. 2008. Corpora and collocations. In Kytö M Lüdeling A, editor, Corpus Linguistics. An International Handbook, pages 1212–1248. Mouton de Gruyter, Berlin, New York. find
  15. John Rupert Firth. 1957. A synopsis of linguistic theory 1930–1955. In Studies in Linguistic Analysis, pages 1–32. Basil Blackwell, Oxford. find
  16. Marcos Garcia and Marcos García Salido. 2019. A Method to Automatically Identify Diachronic Variation in Collocations. In Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, pages 71–80, Florence, Italy. Association for Computational Linguistics. find
  17. Dirk Geeraerts. 1997. Diachronic Prototype Semantics: A Contribution Historical Lexicology. Oxford University Press. find
  18. Dirk Geeraerts, Dirk Speelman, Kris Heylen, Mariana Montes, Stefano De Pascale, Karlien Franco, and Michael Lang. 2023. Lexical Variation and Change: A Distributional Semantic Approach, 1 edition. Oxford University Press. find
  19. Mario Giulianelli, Marco Del Tredici, and Raquel Fernández. 2020. Analysing Lexical Semantic Change with Contextualised Word Representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3960– 3973, Online. Association for Computational Linguistic… find our card
  20. Kristina Gulordava and Marco Baroni. 2011. A distributional similarity approach to the detection of semantic change in the Google Books Ngram corpus. In Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics, pages 67–71, Edinburgh, UK. Association for Computationa… find
  21. Patrick Hanks. 2013. Lexical Analysis: Norms and Exploitations. The MIT Press. find
  22. Zellig S. Harris. 1954. Distributional Structure. WORD, 10(2-3):146–162. Publisher: Routledge. find
  23. Bryan Jurish. 2015. DiaCollo: On the trail of diachronic collocations. In CLARIN Annual Conference 2015 (Wroław, Poland, October 15–17 2015), pages 28–31. find
  24. Bryan Jurish and Maret Nieländer. 2020. Using Dia-Collo for Historical Research. In Selected Papers from the CLARIN Annual Conference 2019, pages 33–40. find
  25. Adam Kilgarriff, Vít Baisa, Jan Bušta, Miloš Jakubíček, Vojtěch Kovář, Jan Michelfeit, Pavel Rychlý, and Vít Suchomel. 2014. The Sketch Engine: ten years on. Lexicography, 1:7–36. Publisher: Springer. find
  26. Yoon Kim, Yi-I Chiu, Kentaro Hanaki, Darshan Hegde, and Slav Petrov. 2014. Temporal Analysis of Language through Neural Language Models. In Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science, pages 61–65, Baltimore, MD, USA. Association for Computational L… find
  27. Vivek Kulkarni, Rami Al-Rfou, Bryan Perozzi, and Steven Skiena. 2015. Statistically Significant Detection of Linguistic Change. In Proceedings of the 24th International Conference on World Wide Web, WWW ’15, pages 625–635, Republic and Canton of Geneva, CHE. International World Wide Web Conferences… find
  28. S. Kullback and R. A. Leibler. 1951. On Information and Sufficiency. The Annals of Mathematical Statistics, 22(1):79–86. find
  29. Andrey Kutuzov, Lidia Pivovarova, and Mario Giulianelli. 2021. Grammatical Profiling for Semantic Change Detection. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 423–434, Online. Association for Computational Linguistics. find
  30. Andrey Kutuzov, Lilja Øvrelid, Terrence Szymanski, and Erik Velldal. 2018. Diachronic word embeddings and semantic shifts: a survey. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1384–1397, Santa Fe, New Mexico, USA. Association for Computational Linguistics… find our card
  31. Omer Levy and Yoav Goldberg. 2014. Dependency-based word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 302–308, Baltimore, Maryland. Association for Computational Linguistics. find
  32. Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Neural Information Processing Systems. find our card
  33. Andreas Madsen, Siva Reddy, and Sarath Chandar. 2022. Post-hoc interpretability for neural nlp: A survey. ACM Computing Surveys, 55(8):1–42. find
  34. Tony McEnery, Vaclav Brezina, and Helen Baker. 2019. Usage Fluctuation Analysis: A new way of analysing shifts in historical discourse. International Journal of Corpus Linguistics, pages 413–444. find
  35. M.L. Menéndez, J.A. Pardo, L. Pardo, and M.C. Pardo. 1997. The Jensen-Shannon divergence. Journal of the Franklin Institute, 334(2):307–318. find
  36. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. ArXiv:1301.3781 [cs]. find
  37. Syrielle Montariol, Matej Martinc, and Lidia Pivovarova. 2021. Scalable and Interpretable Semantic Change Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4642–4652, Online. Association… find
  38. Alan Partington. 1998. Patterns and Meanings. John Benjamins. find
  39. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics. find
  40. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep Contextualized Word Representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Techno… find
  41. Daniela Pettersson-Traba. 2021. Measuring semantic distance across time. Journal of Research Design and Statistics in Linguistics and Communication Science, 6(2):138–165. find
  42. Bach Phan-Tat. 2025. Synflow. find
  43. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. ArXiv:2003.07082 [cs]. find our card
  44. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,… find
  45. Marco Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. “why should I trust you?”: Explaining the predictions of any classifier. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 97–101, San Diego, California.… find our card
  46. Pavel Rychlý. 2008. A Lexicographer-Friendly Association Score. Proc. 2nd Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN, 2:6–9. Publisher: Masaryk University. find our card
  47. Anastasiia Ryzhova, Daria Ryzhova, and Ilya Sochenkov. 2021. Detection of semantic changes in russian nouns with distributional models and grammatical features. In Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2021”. find
  48. Dominik Schlechtweg, Barbara McGillivray, Simon Hengchen, Haim Dubossarsky, and Nina Tahmasebi. 2020. SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1–23, Barcelona (online). International Committee for Com… find our card
  49. Dominik Schlechtweg, Sabine Schulte im Walde, and Stefanie Eckmann. 2018. Diachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… find
  50. Hinrich Schütze. 1998. Automatic Word Sense Discrimination. Computational Linguistics, 24(1):97–123. Place: Cambridge, MA Publisher: MIT Press. find our card
  51. V. Seretan. 2011. Syntax-Based Collocation Extraction. Text, Speech and Language Technology. Springer Netherlands. find
  52. John Sinclair. 1991. Corpus, Concordance, Collocation. Oxford University Press. find
  53. Michael Stubbs. 1995. Collocations and semantic profiles: On the cause of the trouble with quantitative studies. Functions of Language, 2(1):23–55. Publisher: John Benjamins Type: Journal Article. find
  54. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning. find
  55. Nina Tahmasebi, Lars Borin, and Adam Jatowt. 2021. Survey of computational approaches to lexical semantic change detection. In Computational approaches to semantic change. Zenodo. find
  56. Nina Tahmasebi and Haim Dubossarsky. 2023. Computational modeling of semantic change. find
  57. Xiaohang Tang, Yi Zhou, Taichi Aida, Procheta Sen, and Danushka Bollegala. 2023. Can word sense distribution detect semantic changes of words? In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3575–3590, Singapore. Association for Computational Linguistics. find
  58. Charles Truong, Laurent Oudre, and Nicolas Vayatis. 2020. Selective review of offline change point detection methods. Signal Processing, 167:107299. find
  59. Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, and Partha Talukdar. 2019. Incorporating syntactic and semantic information in word embeddings using graph convolutional networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Lin… find

↑ back to top

This page in Markdown →