@inproceedings{L16-1147,
 abstract = {We present a new major release of the OpenSubtitles collection of parallel corpora. The release is compiled from a large database of movie and TV subtitles and includes a total of 1689 bitexts spanning 2.6 billion sentences across 60 languages. The release also incorporates a number of enhancements in the preprocessing and alignment of the subtitles, such as the automatic correction of OCR errors and the use of meta-data to estimate the quality of each subtitle and score subtitle pairs.
},
 address = {Portorož, Slovenia},
 author = {Pierre Lison and Jörg Tiedemann},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {923--929},
 publisher = {European Language Resources Association (ELRA)},
 title = {OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles},
 url = {https://www.aclweb.org/anthology/L16-1147},
 year = {2016}
}