LatinCy: Synthetic Trained Pipelines for Latin NLP

TL;DR

LatinCy provides a set of high-performance, trained NLP pipelines for Latin, enabling researchers to perform various language processing tasks efficiently using spaCy.

Contribution

It introduces LatinCy, the first comprehensive set of trained Latin NLP models integrated with spaCy, trained on extensive Latin datasets including Universal Dependency treebanks.

Findings

POS tagging accuracy of 97.41%

Lemmatization accuracy of 94.66%

Morphological tagging accuracy of 92.76%

Abstract

This paper introduces LatinCy, a set of trained general purpose Latin-language "core" pipelines for use with the spaCy natural language processing framework. The models are trained on a large amount of available Latin data, including all five of the Latin Universal Dependency treebanks, which have been preprocessed to be compatible with each other. The result is a set of general models for Latin with good performance on a number of natural language processing tasks (e.g. the top-performing model yields POS tagging, 97.41% accuracy; lemmatization, 94.66% accuracy; morphological tagging 92.76% accuracy). The paper describes the model training, including its training data and parameterization, and presents the advantages to Latin-language researchers of having a spaCy model available for NLP work.