Please enter a Latin text!
Note: In order to avoid time out from the server, input longer than 50000 characters will be truncated. Sorry about that!
August 2017: More meters added! The macronizer can now handle hendecasyllables as well as distichs of iambic trimeters and dimeters (Beātus ille quī procul negōtiīs...).
May 2017: I have now made the macronized text editable, which means that it will now be much easier to correct typos or misspellings while proofreading the text.
October 2016: The performance on texts written in all uppercase letters has been greatly improved.
July 2016: I am happy to announce that the Macronizer now is able to take the meter into account when guessing the vowel lengths in poetry. When tested on a couple of books of the Aeneid (from the eminent Dickinson College Commentaries), this has been demonstrated to cut the number of erroneous vowel lengths in half! Currently, dactylic hexameters and elegiac distichs are supported; other meters may be added.
Also, I have now added a PayPal donation button: if you use the macronizer regularly and find it helpful and time-saving, please consider making a donation, to support maintenance and continuous development! Any amount is very much appreciated!
This automatic macronizer lets you quickly mark all the long vowels in a Latin text. The expected accuracy on an average classical text is estimated to be about 98% to 99%. Please review the resulting macrons with a critical eye!
The macronization is performed using a part-of-speech tagger (RFTagger) trained on the Latin Dependency Treebank, and with macrons provided by a customized version of the Morpheus morphological analyzer. An earlier version of this tool was the subject of my bachelor’s thesis in Language Technology, Automatic annotation of Latin vowel length.
If you want to run the macronizer locally, or develop it further, you may find the source code on GitHub.
Copyright 2015-2021 Johan Winge. Please send comments to johan.winge@gmail.com.