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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change |
| Publisher | Association for Computational Linguistics |
| Publication date | 2019 |
| Pages | 86-91 |
| DOIs | |
| Publication status | Published - 2019 |
| Event | Computational Approaches to Historical Language Change 2019: Workshop co-located with ACL 2019 - Florence, Italy Duration: 2 Aug 2019 → 2 Aug 2019 https://languagechange.org/events/2019-acl-lcworkshop/ |
Workshop
| Workshop | Computational Approaches to Historical Language Change 2019 |
|---|---|
| Country/Territory | Italy |
| City | Florence |
| Period | 02/08/2019 → 02/08/2019 |
| Internet address |