@article{oai:ipsj.ixsq.nii.ac.jp:00238006,
 author = {Haiyue, Song and Raj, Dabre and Chenhui, Chu and Atsushi, Fujita and Sadao, Kurohashi and Haiyue, Song and Raj, Dabre and Chenhui, Chu and Atsushi, Fujita and Sadao, Kurohashi},
 issue = {8},
 journal = {情報処理学会論文誌},
 month = {Aug},
 note = {Lecture transcript translation helps learners understand online courses; however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel corpus mining, which provides a quick and effective way to mine a parallel corpus from publicly available lectures on Coursera. To create the parallel corpora, we propose a dynamic programming based sentence alignment algorithm which leverages the cosine similarity of machine-translated sentences. The sentence alignment F1 score reaches 96%, which is higher than using the BERTScore, LASER, or sentBERT methods. For both English-Japanese and English-Chinese lecture translations, we extracted parallel corpora of approximately 50,000 lines and created development and test sets through manual filtering for benchmarking translation performance. Through machine translation experiments, we show that the mined corpora enhance the quality of lecture transcript translation when used in conjunction with out-of-domain parallel corpora via multistage fine-tuning. Furthermore, this study also suggests guidelines for gathering and cleaning corpora, mining parallel sentences, cleaning noise in the mined data, and creating high-quality evaluation splits. For the sake of reproducibility, we have released the corpora as well as the code to create them.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.32(2024) (online)
DOI　http://dx.doi.org/10.2197/ipsjjip.32.628
------------------------------, Lecture transcript translation helps learners understand online courses; however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel corpus mining, which provides a quick and effective way to mine a parallel corpus from publicly available lectures on Coursera. To create the parallel corpora, we propose a dynamic programming based sentence alignment algorithm which leverages the cosine similarity of machine-translated sentences. The sentence alignment F1 score reaches 96%, which is higher than using the BERTScore, LASER, or sentBERT methods. For both English-Japanese and English-Chinese lecture translations, we extracted parallel corpora of approximately 50,000 lines and created development and test sets through manual filtering for benchmarking translation performance. Through machine translation experiments, we show that the mined corpora enhance the quality of lecture transcript translation when used in conjunction with out-of-domain parallel corpora via multistage fine-tuning. Furthermore, this study also suggests guidelines for gathering and cleaning corpora, mining parallel sentences, cleaning noise in the mined data, and creating high-quality evaluation splits. For the sake of reproducibility, we have released the corpora as well as the code to create them.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.32(2024) (online)
DOI　http://dx.doi.org/10.2197/ipsjjip.32.628
------------------------------},
 title = {Bilingual Corpus Mining and Multistage Fine-tuning for Improving Machine Translation of Lecture Transcripts},
 volume = {65},
 year = {2024}
}