Corpus and Models for Lemmatisation and POS-tagging of Old French

TL;DR

This paper presents a neural approach to lemmatization and POS tagging for Old French, leveraging dedicated corpora to address the language's variation and resource scarcity.

Contribution

It introduces new neural models and a corpus construction methodology specifically tailored for Old French linguistic analysis.

Findings

Successful development of lemmatization and POS-tagging models for Old French

Demonstrated the effectiveness of neural taggers on historic language data

Progress in creating dedicated corpora for under-resourced languages

Abstract

Old French is a typical example of an under-resourced historic languages, that furtherly displays animportant amount of linguistic variation. In this paper, we present the current results of a long going project (2015-...) and describe how we broached the difficult question of providing lemmatisation andPOS models for Old French with the help of neural taggers and the progressive constitution of dedicated corpora.