Punctuation Prediction for Polish Texts using Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Pokrywka, Jakub
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910636705841152
author Pokrywka, Jakub
author_facet Pokrywka, Jakub
contents Speech recognition systems typically output text lacking punctuation. However, punctuation is crucial for written text comprehension. To tackle this problem, Punctuation Prediction models are developed. This paper describes a solution for Poleval 2022 Task 1: Punctuation Prediction for Polish Texts, which scores 71.44 Weighted F1. The method utilizes a single HerBERT model finetuned to the competition data and an external dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Punctuation Prediction for Polish Texts using Transformers
Pokrywka, Jakub
Computation and Language
Speech recognition systems typically output text lacking punctuation. However, punctuation is crucial for written text comprehension. To tackle this problem, Punctuation Prediction models are developed. This paper describes a solution for Poleval 2022 Task 1: Punctuation Prediction for Polish Texts, which scores 71.44 Weighted F1. The method utilizes a single HerBERT model finetuned to the competition data and an external dataset.
title Punctuation Prediction for Polish Texts using Transformers
topic Computation and Language
url https://arxiv.org/abs/2410.04621