Saved in:
Bibliographic Details
Main Author: Celano, Giuseppe G. A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.12055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909351365574656
author Celano, Giuseppe G. A.
author_facet Celano, Giuseppe G. A.
contents This paper presents an experiment consisting in the comparison of six models to identify a state-of-the-art morphosyntactic parser and lemmatizer for Ancient Greek capable of annotating according to the Ancient Greek Dependency Treebank annotation scheme. A normalized version of the major collections of annotated texts was used to (i) train the baseline model Dithrax with randomly initialized character embeddings and (ii) fine-tune Trankit and four recent models pretrained on Ancient Greek texts, i.e., GreBERTa and PhilBERTa for morphosyntactic annotation and GreTA and PhilTa for lemmatization. A Bayesian analysis shows that Dithrax and Trankit annotate morphology practically equivalently, while syntax is best annotated by Trankit and lemmata by GreTa. The results of the experiment suggest that token embeddings are not sufficient to achieve high UAS and LAS scores unless they are coupled with a modeling strategy specifically designed to capture syntactic relationships. The dataset and best-performing models are made available online for reuse.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12055
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A State-of-the-Art Morphosyntactic Parser and Lemmatizer for Ancient Greek
Celano, Giuseppe G. A.
Computation and Language
This paper presents an experiment consisting in the comparison of six models to identify a state-of-the-art morphosyntactic parser and lemmatizer for Ancient Greek capable of annotating according to the Ancient Greek Dependency Treebank annotation scheme. A normalized version of the major collections of annotated texts was used to (i) train the baseline model Dithrax with randomly initialized character embeddings and (ii) fine-tune Trankit and four recent models pretrained on Ancient Greek texts, i.e., GreBERTa and PhilBERTa for morphosyntactic annotation and GreTA and PhilTa for lemmatization. A Bayesian analysis shows that Dithrax and Trankit annotate morphology practically equivalently, while syntax is best annotated by Trankit and lemmata by GreTa. The results of the experiment suggest that token embeddings are not sufficient to achieve high UAS and LAS scores unless they are coupled with a modeling strategy specifically designed to capture syntactic relationships. The dataset and best-performing models are made available online for reuse.
title A State-of-the-Art Morphosyntactic Parser and Lemmatizer for Ancient Greek
topic Computation and Language
url https://arxiv.org/abs/2410.12055