Abstract
We build parfda Moses statistical machine translation (SMT) models for most language pairs in the news translation task. We experiment with a hybrid approach using neural language models integrated into Moses. We obtain the constrained data statistics on the machine translation task, the coverage of the test sets, and the upper bounds on the translation results. We also contribute a new testsuite for the German-English language pair and a new automated key phrase extraction technique for the evaluation of the testsuite translations.- Anthology ID:
- W19-5306
- Original:
- W19-5306v1
- Version 2:
- W19-5306v2
- Version 3:
- W19-5306v3
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 122–128
- Language:
- URL:
- https://aclanthology.org/W19-5306
- DOI:
- 10.18653/v1/W19-5306
- Cite (ACL):
- Ergun Biçici. 2019. Machine Translation with parfda, Moses, kenlm, nplm, and PRO. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 122–128, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Machine Translation with parfda, Moses, kenlm, nplm, and PRO (Biçici, WMT 2019)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/W19-5306.pdf