Multilingual Neural Machine Translation has been showing great success using transformer models. Deploying these models is challenging because they usually require large vocabulary (vocab) sizes for various languages. This limits the speed of predicting the output tokens in the last vocab projection layer. To alleviate these challenges, this paper proposes a fast vocabulary projection method via clustering which can be used for multilingual transformers on GPUs. First, we offline split the vocab search space into disjoint clusters given the hidden context vector of the decoder output, which results in much smaller vocab columns for vocab projection. Second, at inference time, the proposed method predicts the clusters and candidate active tokens for hidden context vectors at the vocab projection. This paper also includes analysis of different ways of building these clusters in multilingual settings. Our results show end-to-end speed gains in float16 GPU inference up to 25% while maintaining the BLEU score and slightly increasing memory cost. The proposed method speeds up the vocab projection step itself by up to 2.6x. We also conduct an extensive human evaluation to verify the proposed method preserves the quality of the translations from the original model.

This paper proposes a simple and effective method to improve direct translation for the zero-shot case and when direct data is available. We modify the input tokens at both the encoder and decoder to include signals for the source and target languages. We show a performance gain when training from scratch, or finetuning a pretrained model with the proposed setup. In in-house experiments, our method shows nearly a 10.0 BLEU points difference depending on the stoppage criteria. In a WMT-based setting, we see 1.3 and 0.4 BLEU points improvement for the zero-shot setting, and when using direct data for training, respectively, while from-English performance improves by 4.17 and 0.85 BLEU points. In the low-resource setting, we see a 1.5 ∼ 1.7 point improvement when finetuning on directly translated domain data.

This paper presents Domain-Specific Sub-network (DoSS). It uses a set of masks obtained through pruning to define a sub-network for each domain and finetunes the sub-network parameters on domain data. This performs very closely and drastically reduces the number of parameters compared to finetuning the whole network on each domain. Also a method to make masks unique per domain is proposed and shown to greatly improve the generalization to unseen domains. In our experiments on German to English machine translation the proposed method outperforms the strong baseline of continue training on multi-domain (medical, tech and religion) data by 1.47 BLEU points. Also continue training DoSS on new domain (legal) outperforms the multi-domain (medical, tech, religion, legal) baseline by 1.52 BLEU points.

This paper describes the Microsoft Egypt Development Center (EgDC) submission to the constrained track of WMT21 shared news translation task. We focus on the three relatively low resource language pairs Bengali ↔ Hindi, English ↔ Hausa and Xhosa ↔ Zulu. To overcome the limitation of relatively low parallel data we train a multilingual model using a multitask objective employing both parallel and monolingual data. In addition, we augment the data using back translation. We also train a bilingual model incorporating back translation and knowledge distillation then combine the two models using sequence-to-sequence mapping. We see around 70% relative gain in BLEU point for En ↔ Ha and around 25% relative improvements for Bn ↔ Hi and Xh ↔ Zu compared to bilingual baselines.

This paper presents the description of our submission to WMT20 sentence filtering task. We combine scores from custom LASER built for each source language, a classifier built to distinguish positive and negative pairs and the original scores provided with the task. For the mBART setup, provided by the organizers, our method shows 7% and 5% relative improvement, over the baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.