# Microsoft Research Asia's Systems for WMT19

arXiv: https://arxiv.org/abs/1911.06191 · HTML: https://mlsanity.com/paper/1911.06191/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2019.

## Built on by (most cited first, 10 of 10)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model](https://mlsanity.com/paper/2208.01448/) (2022)
- [Using natural language prompts for machine translation](https://mlsanity.com/paper/2202.11822/) (2022)
- [Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models](https://mlsanity.com/paper/2204.00471/) (2022)
- [Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling](https://mlsanity.com/paper/2205.12986/) (2022)
- [Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort](https://mlsanity.com/paper/2105.13385/) (2021)
- [Onception: Active Learning with Expert Advice for Real World Machine Translation](https://mlsanity.com/paper/2203.04507/) (2022)
- [Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios](https://mlsanity.com/paper/2305.19757/) (2023)

## Abstract (arXiv)

We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rececent techniques to enhance the baseline systems: multi-agent dual learning (MADL), masked sequence-to-sequence pre-training (MASS), neural architecture optimization (NAO), and soft contextual data augmentation (SCA).