What Would Cicero Write?
Recent developments in Transformer language models now allow users to predict the probability of different sentences and to predict missing words more accurately than before. This new information and perspective can be used to form judgments on novel textual emendations and to further quantify exist...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | German |
| Published: |
Università degli Studi di Torino
2021-12-01
|
| Series: | Ciceroniana On Line |
| Online Access: | https://www.ojs.unito.it/index.php/COL/article/view/6523 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Recent developments in Transformer language models now allow users to predict the probability of different sentences and to predict missing words more accurately than before. This new information and perspective can be used to form judgments on novel textual emendations and to further quantify existing historical editorial judgments. We examine the importance of analyzing an author’s corpus, and the impact of the Good-Turing theory of frequency estimation when predicting missing words. We will also outline some of the limits of what Transformer language models can do, and how to practically evaluate them. |
|---|---|
| ISSN: | 2532-5299 2532-5353 |