Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corpora

@inproceedings{ranathunga2024quality,
  title={Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corpora},
  author={Ranathunga, Surangika and de Silva, Nisansa and Velayuthan, Menan and Fernando, Aloka and Rathnayake, Charitha},
  booktitle ={Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
   month = {03},
    address = {St. Julian{'}s, Malta},
    publisher = {Association for Computational Linguistics},
    url = {https://aclanthology.org/2024.eacl-long.52},
    pages = {860--880},
  abstract={We conducted a detailed analysis on the quality of web-mined corpora for two low-resource languages (making three language pairs, English-Sinhala, English-Tamil and Sinhala-Tamil). We ranked each corpus according to a similarity measure and carried out an intrinsic and extrinsic evaluation on different portions of this ranked corpus. We show that there are significant quality differences between different portions of web-mined corpora and that the quality varies across languages and datasets. We also show that, for some web-mined datasets, Neural Machine Translation (NMT) models trained with their highest-ranked 25k portion can be on par with human-curated datasets.},
  year={2024},
  misc={https://arxiv.org/pdf/2402.07446.pdf,NLP:SIN,https://goo.gl/iY6aTr}
}