COLING 2020main5 citations
Neural text normalization leveraging similarities of strings and sounds
Riku Kawamura, Tatsuya Aoki, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura
Abstract
We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline. Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters. So that the proposed models achieved higher F1 scores than the baseline.
BibTeX
@inproceedings{kawamura-etal-2020-neural,
title = "Neural text normalization leveraging similarities of strings and sounds",
author = "Kawamura, Riku and
Aoki, Tatsuya and
Kamigaito, Hidetaka and
Takamura, Hiroya and
Okumura, Manabu",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.192/",
doi = "10.18653/v1/2020.coling-main.192",
pages = "2126--2131"
}