Abstract | ||
---|---|---|
This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track. Our system is built based on the Transformer model with novel techniques borrowed from our recent research work. For the data filtering, language-model-based and rule-based methods are conducted to filter the data to obtain high-quality bilingual parallel corpora. We also strengthen our system with some dominating techniques related to data augmentation, such as knowledge distillation, tagged back-translation, and iterative back-translation. We also incorporate novel training techniques such as R-drop, deep model, and large batch training which have been shown to be beneficial to the naive Transformer model. In the SST scenario, several variations of extttwait-k strategies are explored. Furthermore, in terms of robustness, both data-based and model-based ways are used to reduce the sensitivity of our system to Automatic Speech Recognition (ASR) outputs. We finally design some inference algorithms and use the adaptive-ensemble method based on multiple model variants to further improve the performance of the system. Compared with strong baselines, fusing all techniques can improve our system by 2 extasciitilde3 BLEU scores under different latency regimes. |
Year | DOI | Venue |
---|---|---|
2022 | 10.18653/v1/2022.iwslt-1.17 | International Conference on Spoken Language Translation (IWSLT) |
DocType | Volume | Citations |
Conference | Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022) | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bao Guo | 1 | 0 | 0.34 |
Mengge Liu | 2 | 0 | 0.34 |
Wen Zhang | 3 | 6 | 8.84 |
Hexuan Chen | 4 | 0 | 0.34 |
Chang Mu | 5 | 0 | 0.34 |
Xiang Li (李翔) | 6 | 0 | 3.04 |
Jianwei Cui | 7 | 5 | 5.23 |
Bin Wang | 8 | 95 | 11.84 |
Yuhang Guo | 9 | 2 | 2.76 |