Improving Latin Dependency Parsing by Combining Treebanks and Predictions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AIHFX53EU" target="_blank" >RIV/00216208:11320/25:IHFX53EU - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85216580264&partnerID=40&md5=ef3021de3b5b84c97577b16b7f7d7772" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85216580264&partnerID=40&md5=ef3021de3b5b84c97577b16b7f7d7772</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Latin Dependency Parsing by Combining Treebanks and Predictions

Popis výsledku v původním jazyce

This paper introduces new models designed to improve the morpho-syntactic parsing of the five largest Latin treebanks in the Universal Dependencies (UD) framework.First, using two state-of-the-art parsers, Trankit and Stanza, along with our custom UD tagger, we train new models on the five treebanks both individually and by combining them into novel merged datasets.We also test the models on the CIRCSE test set.In an additional experiment, we evaluate whether this set can be accurately tagged using the novel LASLA corpus (https://github.com/CIRCSE/LASLA).Second, we aim to improve the results by combining the predictions of different models through an atomic morphological feature voting system.The results of our two main experiments demonstrate significant improvements, particularly for the smaller treebanks, with LAS scores increasing by 16.10 and 11.85%-points for UDante and Perseus, respectively (Gamba and Zeman, 2023a).Additionally, the voting system for morphological features (FEATS) brings improvements, especially for the smaller Latin treebanks: Perseus 3.15% and CIRCSE 2.47%-points.Tagging the CIRCSE set with our custom model using the LASLA model improves POS 6.71 and FEATS 11.04%-points compared to our best-performing UD PROIEL model.Our results show that larger datasets and ensemble predictions can significantly improve performance. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

Improving Latin Dependency Parsing by Combining Treebanks and Predictions

Popis výsledku anglicky

This paper introduces new models designed to improve the morpho-syntactic parsing of the five largest Latin treebanks in the Universal Dependencies (UD) framework.First, using two state-of-the-art parsers, Trankit and Stanza, along with our custom UD tagger, we train new models on the five treebanks both individually and by combining them into novel merged datasets.We also test the models on the CIRCSE test set.In an additional experiment, we evaluate whether this set can be accurately tagged using the novel LASLA corpus (https://github.com/CIRCSE/LASLA).Second, we aim to improve the results by combining the predictions of different models through an atomic morphological feature voting system.The results of our two main experiments demonstrate significant improvements, particularly for the smaller treebanks, with LAS scores increasing by 16.10 and 11.85%-points for UDante and Perseus, respectively (Gamba and Zeman, 2023a).Additionally, the voting system for morphological features (FEATS) brings improvements, especially for the smaller Latin treebanks: Perseus 3.15% and CIRCSE 2.47%-points.Tagging the CIRCSE set with our custom model using the LASLA model improves POS 6.71 and FEATS 11.04%-points compared to our best-performing UD PROIEL model.Our results show that larger datasets and ensemble predictions can significantly improve performance. © 2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

NLP4DH - Int. Conf. Nat. Lang. Process. Digit. Humanit., Proc. Conf.

ISBN

979-889176181-0

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

216-228

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

Miami

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—