Integrated Sequence Tagging for Medieval Latin Using Deep Representation Learning

TL;DR

This paper introduces an integrated deep learning approach for part-of-speech tagging and lemmatization of medieval Latin, addressing orthographic variation and reducing error propagation compared to traditional lexicon-dependent methods.

Contribution

It proposes a novel layered neural network architecture that jointly performs sequence tagging tasks, improving over cascaded and lexicon-dependent approaches in medieval Latin processing.

Findings

Effective handling of orthographic variation in medieval Latin

Reduction in error propagation compared to traditional methods

Demonstrated improved accuracy in PoS tagging and lemmatization

Abstract

In this paper we consider two sequence tagging tasks for medieval Latin: part-of-speech tagging and lemmatization. These are both basic, yet foundational preprocessing steps in applications such as text re-use detection. Nevertheless, they are generally complicated by the considerable orthographic variation which is typical of medieval Latin. In Digital Classics, these tasks are traditionally solved in a (i) cascaded and (ii) lexicon-dependent fashion. For example, a lexicon is used to generate all the potential lemma-tag pairs for a token, and next, a context-aware PoS-tagger is used to select the most appropriate tag-lemma pair. Apart from the problems with out-of-lexicon items, error percolation is a major downside of such approaches. In this paper we explore the possibility to elegantly solve these tasks using a single, integrated approach. For this, we make use of a layered neural network architecture from the field of deep representation learning.