Identifying Temporal Trends Based on Perplexity and Clustering: Are We Looking at Language Change?

Sidsel Boldsen, Manex Agirrezabal, Patrizia Paggio


Abstract
In this work we propose a data-driven methodology for identifying temporal trends in a corpus of medieval charters. We have used perplexities derived from RNNs as a distance measure between documents and then, performed clustering on those distances. We argue that perplexities calculated by such language models are representative of temporal trends. The clusters produced using the K-Means algorithm give an insight of the differences in language in different time periods at least partly due to language change. We suggest that the temporal distribution of the individual clusters might provide a more nuanced picture of temporal trends compared to discrete bins, thus providing better results when used in a classification task.
Anthology ID:
W19-4711
Volume:
Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Nina Tahmasebi, Lars Borin, Adam Jatowt, Yang Xu
Venue:
LChange
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
86–91
Language:
URL:
https://aclanthology.org/W19-4711
DOI:
10.18653/v1/W19-4711
Bibkey:
Cite (ACL):
Sidsel Boldsen, Manex Agirrezabal, and Patrizia Paggio. 2019. Identifying Temporal Trends Based on Perplexity and Clustering: Are We Looking at Language Change?. In Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, pages 86–91, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Identifying Temporal Trends Based on Perplexity and Clustering: Are We Looking at Language Change? (Boldsen et al., LChange 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4711.pdf