SUMAT: Data Collection and Parallel Corpus Compilation for Machine Translation of Subtitles

Volha Petukhova, Rodrigo Agerri, Mark Fishel, Sergio Penkale, Arantza del Pozo, Mirjam Sepesy Maucec, Andy Way, Panayota Georgakopoulou, Martin Volk. SUMAT: Data Collection and Parallel Corpus Compilation for Machine Translation of Subtitles. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet Ugur Dogan, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, editors, Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012), Istanbul, Turkey, May 23-25, 2012. pages 21-28, European Language Resources Association (ELRA), 2012. [doi]

@inproceedings{PetukhovaAFPPMWGV12,
  title = {SUMAT: Data Collection and Parallel Corpus Compilation for Machine Translation of Subtitles},
  author = {Volha Petukhova and Rodrigo Agerri and Mark Fishel and Sergio Penkale and Arantza del Pozo and Mirjam Sepesy Maucec and Andy Way and Panayota Georgakopoulou and Martin Volk},
  year = {2012},
  url = {http://www.lrec-conf.org/proceedings/lrec2012/summaries/154.html},
  researchr = {https://researchr.org/publication/PetukhovaAFPPMWGV12},
  cites = {0},
  citedby = {0},
  pages = {21-28},
  booktitle = {Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012), Istanbul, Turkey, May 23-25, 2012},
  editor = {Nicoletta Calzolari and Khalid Choukri and Thierry Declerck and Mehmet Ugur Dogan and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {978-2-9517408-7-7},
}