Neural spell-checker: Beyond words with synthetic data generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Klemen, Matej, Božič, Martin, Holdt, Špela Arhar, Robnik-Šikonja, Marko
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910678856499200
author Klemen, Matej
Božič, Martin
Holdt, Špela Arhar
Robnik-Šikonja, Marko
author_facet Klemen, Matej
Božič, Martin
Holdt, Špela Arhar
Robnik-Šikonja, Marko
contents Spell-checkers are valuable tools that enhance communication by identifying misspelled words in written texts. Recent improvements in deep learning, and in particular in large language models, have opened new opportunities to improve traditional spell-checkers with new functionalities that not only assess spelling correctness but also the suitability of a word for a given context. In our work, we present and compare two new spell-checkers and evaluate them on synthetic, learner, and more general-domain Slovene datasets. The first spell-checker is a traditional, fast, word-based approach, based on a morphological lexicon with a significantly larger word list compared to existing spell-checkers. The second approach uses a language model trained on a large corpus with synthetically inserted errors. We present the training data construction strategies, which turn out to be a crucial component of neural spell-checkers. Further, the proposed neural model significantly outperforms all existing spell-checkers for Slovene in both precision and recall.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23514
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural spell-checker: Beyond words with synthetic data generation
Klemen, Matej
Božič, Martin
Holdt, Špela Arhar
Robnik-Šikonja, Marko
Computation and Language
Spell-checkers are valuable tools that enhance communication by identifying misspelled words in written texts. Recent improvements in deep learning, and in particular in large language models, have opened new opportunities to improve traditional spell-checkers with new functionalities that not only assess spelling correctness but also the suitability of a word for a given context. In our work, we present and compare two new spell-checkers and evaluate them on synthetic, learner, and more general-domain Slovene datasets. The first spell-checker is a traditional, fast, word-based approach, based on a morphological lexicon with a significantly larger word list compared to existing spell-checkers. The second approach uses a language model trained on a large corpus with synthetically inserted errors. We present the training data construction strategies, which turn out to be a crucial component of neural spell-checkers. Further, the proposed neural model significantly outperforms all existing spell-checkers for Slovene in both precision and recall.
title Neural spell-checker: Beyond words with synthetic data generation
topic Computation and Language
url https://arxiv.org/abs/2410.23514