Facebook AI’s WAT19 Myanmar-English Translation Task Submission
By Peng-Jen Chen, Jiajun Shen, Matt Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc'Aurelio Ranzato. 2019
29 citations recorded by the source corpus.
This paper describes Facebook AI’s submission to the WAT 2019 Myanmar-English translation task. Our baseline systems are BPE-based transformer models. We explore methods to leverage monolingual data to improve generalization, including self-training, back-translation and their combination. We further improve results by using noisy channel re-ranking and ensembling. We demonstrate that these techniques can significantly improve not only a system trained with additional monolingual data, but even the baseline system trained exclusively on the provided small parallel dataset. Our system ranks first in both directions according to human evaluation and BLEU, with a gain of over 8 BLEU points above the second best system.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Luke S. Zettlemoyer
- Graham Neubig
- Jiatao Gu
- Michael Lewis
- Mohit Bansal
- Michael Auli
- Furu Wei
- Noah A. Smith
Citations in the corpus
- Multilingual Denoising Pre-training for Neural Machine Translation (2020, methodology): “same monolingual data where we use 79M En and 29M My sentences following Chen et al. (2019).”
- The Source-Target Domain Mismatch Problem in Machine Translation (2019, methodology): “We report the system performance on the ALT test set following the same evaluation protocol of the WAT 2019 English-Myanmar subtask, see (Chen et al., 2019) for more details on BLEU calculation.”