Using crowdsourcing, we collected more than 10,000 URL pairs (parallel top page pairs) of bilingual websites that contain parallel documents and created a Japanese-Chinese parallel corpus of 4.6M sentence pairs from these websites. We used a Japanese-Chinese bilingual dictionary of 160K word pairs for document and sentence alignment. We then used high-quality 1.2M Japanese-Chinese sentence pairs to train a parallel corpus filter based on statistical language models and word translation probabilities. We compared the translation accuracy of the model trained on these 4.6M sentence pairs with that of the model trained on Japanese-Chinese sentence pairs from CCMatrix (12.4M), a parallel corpus from global web mining. Although our corpus is only one-third the size of CCMatrix, we found that the accuracy of the two models was comparable and confirmed that it is feasible to use crowdsourcing for web mining of parallel data.

CCMatrix is the largest data set of high-quality, web-based bitexts for training translation models. With more than 4.5 billion parallel sentences in 576 language pairs pulled from snapshots of the CommonCrawl public data set, CCMatrix is more than 50 times larger than the WikiMatrix corpus that we shared last year. Gathering a data set of this size required modifying our previous bitext mining approach used for WikiMatrix, assuming that the translation of one sentence could be found anywhere on CommonCrawl, which functions as an open archive of the internet. To address the significant computational challenges posed by comparing billions of sentences to determine which ones are mutual translations, we used massively parallel processing, as well as our highly efficient FAISS library for fast similarity searches. We're sharing details about how we created CCMatrix, and the tools needed for other researchers to reproduce our results and use this corpus for their work.