# WeChat Neural Machine Translation Systems for WMT20

arXiv: https://arxiv.org/abs/2010.00247 · HTML: https://mlsanity.com/paper/2010.00247/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [Selective Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2105.12967/) (2021)
- [Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand](https://mlsanity.com/paper/2112.04139/) (2021)
- [The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21](https://mlsanity.com/paper/2109.11247/) (2021)
- [WeChat Neural Machine Translation Systems for WMT21](https://mlsanity.com/paper/2108.02401/) (2021)
- [Scheduled Sampling Based on Decoding Steps for Neural Machine Translation](https://mlsanity.com/paper/2108.12963/) (2021)
- [Confidence-Aware Scheduled Sampling for Neural Machine Translation](https://mlsanity.com/paper/2107.10427/) (2021)
- [Onception: Active Learning with Expert Advice for Real World Machine Translation](https://mlsanity.com/paper/2203.04507/) (2022)
- [The NiuTrans Machine Translation Systems for WMT21](https://mlsanity.com/paper/2109.10485/) (2021)
- [BJTU-WeChat's Systems for the WMT22 Chat Translation Task](https://mlsanity.com/paper/2211.15009/) (2022)
- [Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Task](https://mlsanity.com/paper/2211.15022/) (2022)
- [Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation](https://mlsanity.com/paper/2308.03131/) (2023)

## Abstract (arXiv)

We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.