@inproceedings{8a9d5c14ce054d8db3b5d6b4fc930de5,
title = "JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus",
abstract = "Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Although there are billions of parallel sentences for a few language pairs, effectively dealing with most language pairs is difficult due to a lack of publicly available parallel corpora. This paper creates a large parallel corpus for English-Japanese, a language pair for which only limited resources are available, compared to such resource-rich languages as English-German. It introduces a new web-based English-Japanese parallel corpus named JParaCrawl v3.0. Our new corpus contains more than 21 million unique parallel sentence pairs, which is more than twice as many as the previous JParaCrawl v2.0 corpus. Through experiments, we empirically show how our new corpus boosts the accuracy of machine translation models on various domains. The JParaCrawl v3.0 corpus will eventually be publicly available online for research purposes.",
keywords = "English, Japanese, machine translation, parallel corpus",
author = "Makoto Morishita and Katsuki Chousa and Jun Suzuki and Masaaki Nagata",
note = "Funding Information: We gratefully acknowledge the ParaCrawl project for releasing its software and its members with whom we engaged in valuable discussions. We thank the three anonymous reviewers for their comments. Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; 13th International Conference on Language Resources and Evaluation Conference, LREC 2022 ; Conference date: 20-06-2022 Through 25-06-2022",
year = "2022",
language = "English",
series = "2022 Language Resources and Evaluation Conference, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "6704--6710",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Jan Odijk and Stelios Piperidis",
booktitle = "2022 Language Resources and Evaluation Conference, LREC 2022",
}