# Subdiffusive semantic evolution in Indo-European languages

arXiv: https://arxiv.org/abs/2209.04701 · HTML: https://mlsanity.com/paper/2209.04701/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 50 references that are in the map.
- First posted on arXiv 10 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method](https://mlsanity.com/paper/1402.3722/) (2014)
- [Dynamic Word Embeddings](https://mlsanity.com/paper/1702.08359/) (2017)
- [Dynamic Word Embeddings for Evolving Semantic Discovery](https://mlsanity.com/paper/1703.00607/) (2017)
- [A comparative evaluation and analysis of three generations of Distributional Semantic Models](https://mlsanity.com/paper/2105.09825/) (2021)
- [Characterizing the Google Books corpus: Strong limits to inferences of socio-cultural and linguistic evolution](https://mlsanity.com/paper/1501.00960/) (2015)
- [Zipf's law holds for phrases, not words](https://mlsanity.com/paper/1406.5181/) (2014)

## Abstract (arXiv)

How do words change their meaning? Although semantic evolution is driven by a variety of distinct factors, including linguistic, societal, and technological ones, we find that there is one law that holds universally across five major Indo-European languages: that semantic evolution is strongly subdiffusive. Using an automated pipeline of diachronic distributional semantic embedding that controls for underlying symmetries, we show that words follow stochastic trajectories in meaning space with an anomalous diffusion exponent α= 0.45± 0.05 across languages, in contrast with diffusing particles that follow α=1. Randomization methods indicate that preserving temporal correlations in semantic change directions is necessary to recover strongly subdiffusive behavior; however, correlations in change sizes play an important role too. We furthermore show that strong subdiffusion is a robust phenomenon under a wide variety of choices in data analysis and interpretation, such as the choice of fitting an ensemble average of displacements or averaging best-fit exponents of individual word trajectories.