Improved Data Augmentation for Translation Suggestion

• URL: http://arxiv.org/abs/2210.06138v1
• Date: Wed, 12 Oct 2022 12:46:43 GMT
• Title: Improved Data Augmentation for Translation Suggestion
• Authors: Hongxiao Zhang, Siyu Lai, Songming Zhang, Hui Huang, Yufeng Chen, Jinan Xu, Jian Liu
• Abstract summary: This paper introduces the system used in our submission to the WMT'22 Translation Suggestion shared task. We use three strategies to construct synthetic data from parallel corpora to compensate for the lack of supervised data. We rank second and third on the English-German and English-Chinese bidirectional tasks, respectively.
• Score: 28.672227843541656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Translation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT'22 Translation Suggestion shared task. Our system is based on the ensemble of different translation architectures, including Transformer, SA-Transformer, and DynamicConv. We use three strategies to construct synthetic data from parallel corpora to compensate for the lack of supervised data. In addition, we introduce a multi-phase pre-training strategy, adding an additional pre-training phase with in-domain data. We rank second and third on the English-German and English-Chinese bidirectional tasks, respectively.

Related papers

• Neural Machine Translation with Contrastive Translation Memories [71.86990102704311]
  Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. We propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence. In training phase, a Multi-TM contrastive learning objective is introduced to learn salient feature of each TM with respect to target sentence.
  arXiv  Detail & Related papers  (2022-12-06T17:10:17Z)
• Effective General-Domain Data Inclusion for the Machine Translation Task by Vanilla Transformers [0.0]
  We aim at a Transformer-based system that is able to translate a source sentence in German to its counterpart target sentence in English. We perform experiments on the news commentary German-English parallel sentences from the WMT'13 dataset. We find that including the IWSLT'16 dataset in training helps achieve a gain of 2 BLEU score points on the test set of the WMT'13 dataset.
  arXiv  Detail & Related papers  (2022-09-28T13:14:49Z)
• The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task [92.5087402621697]
  This paper describes the submission of our end-to-end YiTrans speech translation system for the IWSLT 2022 offline task. The YiTrans system is built on large-scale pre-trained encoder-decoder models. Our final submissions rank first on English-German and English-Chinese end-to-end systems in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2022-06-12T16:13:01Z)
• Non-Parametric Domain Adaptation for End-to-End Speech Translation [72.37869362559212]
  End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. We propose a novel non-parametric method that leverages domain-specific text translation corpus to achieve domain adaptation for the E2E-ST system.
  arXiv  Detail & Related papers  (2022-05-23T11:41:02Z)
• Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task [95.06453182273027]
  This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. Our model submissions to the shared task were with DeltaLMnotefooturlhttps://aka.ms/deltalm, a generic pre-trained multilingual-decoder model. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2021-11-03T09:16:17Z)
• Improving Neural Machine Translation by Bidirectional Training [85.64797317290349]
  We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs significantly higher.
  arXiv  Detail & Related papers  (2021-09-16T07:58:33Z)
• Tilde at WMT 2020: News Task Systems [0.38073142980733]
  This paper describes Tilde's submission to the WMT 2020 shared task on news translation for both directions of the English-Polish language pair. We build our baseline systems to be morphologically motivated sub-word unit-based Transformer base models. Our final models are ensembles of Transformer base and Transformer big models that feature right-to-left re-ranking.
  arXiv  Detail & Related papers  (2020-10-29T08:59:37Z)
• Explicit Reordering for Neural Machine Translation [50.70683739103066]
  In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency. We propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT. The empirical results on the WMT14 English-to-German, WAT ASPEC Japanese-to-English, and WMT17 Chinese-to-English translation tasks show the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2020-04-08T05:28:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.