The LMU Munich System for the WMT 2020 Unsupervised Machine Translation
Shared Task
- URL: http://arxiv.org/abs/2010.13192v1
- Date: Sun, 25 Oct 2020 19:04:03 GMT
- Title: The LMU Munich System for the WMT 2020 Unsupervised Machine Translation
Shared Task
- Authors: Alexandra Chronopoulou, Dario Stojanovski, Viktor Hangya, Alexander
Fraser
- Abstract summary: This paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions.
Our core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al.
We ensemble our best-performing systems and reach a BLEU score of 32.4 on German->Upper Sorbian and 35.2 on Upper Sorbian->German.
- Score: 125.06737861979299
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper describes the submission of LMU Munich to the WMT 2020
unsupervised shared task, in two language directions, German<->Upper Sorbian.
Our core unsupervised neural machine translation (UNMT) system follows the
strategy of Chronopoulou et al. (2020), using a monolingual pretrained language
generation model (on German) and fine-tuning it on both German and Upper
Sorbian, before initializing a UNMT model, which is trained with online
backtranslation. Pseudo-parallel data obtained from an unsupervised statistical
machine translation (USMT) system is used to fine-tune the UNMT model. We also
apply BPE-Dropout to the low resource (Upper Sorbian) data to obtain a more
robust system. We additionally experiment with residual adapters and find them
useful in the Upper Sorbian->German direction. We explore sampling during
backtranslation and curriculum learning to use SMT translations in a more
principled way. Finally, we ensemble our best-performing systems and reach a
BLEU score of 32.4 on German->Upper Sorbian and 35.2 on Upper Sorbian->German.
Related papers
- Towards Zero-Shot Multimodal Machine Translation [64.9141931372384]
We propose a method to bypass the need for fully supervised data to train multimodal machine translation systems.
Our method, called ZeroMMT, consists in adapting a strong text-only machine translation (MT) model by training it on a mixture of two objectives.
To prove that our method generalizes to languages with no fully supervised training data available, we extend the CoMMuTE evaluation dataset to three new languages: Arabic, Russian and Chinese.
arXiv Detail & Related papers (2024-07-18T15:20:31Z) - Boosting Unsupervised Machine Translation with Pseudo-Parallel Data [2.900810893770134]
We propose a training strategy that relies on pseudo-parallel sentence pairs mined from monolingual corpora and synthetic sentence pairs back-translated from monolingual corpora.
We reach an improvement of up to 14.5 BLEU points (English to Ukrainian) over a baseline trained on back-translated data only.
arXiv Detail & Related papers (2023-10-22T10:57:12Z) - Improving Simultaneous Machine Translation with Monolingual Data [94.1085601198393]
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model.
We propose to leverage monolingual data to improve SiMT, which trains a SiMT student on the combination of bilingual data and external monolingual data distilled by Seq-KD.
arXiv Detail & Related papers (2022-12-02T14:13:53Z) - Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation
System for the WMT22 Translation Task [49.916963624249355]
This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task.
We participate in the general translation task on English$Leftrightarrow$Livonian.
Our system is based on M2M100 with novel techniques that adapt it to the target language pair.
arXiv Detail & Related papers (2022-10-17T04:34:09Z) - Unsupervised Translation of German--Lower Sorbian: Exploring Training
and Novel Transfer Methods on a Low-Resource Language [2.4870937127982344]
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task.
Our system uses a transformer encoder-decoder architecture in which we make three changes to the standard training procedure.
We introduce a novel method for initializing the vocabulary of an unseen language, achieving improvements of 3.2 BLEU for DE$rightarrow$DSB and 4.0 BLEU for DSB$rightarrow$DE.
arXiv Detail & Related papers (2021-09-24T15:11:22Z) - CUNI Systems for the Unsupervised and Very Low Resource Translation Task
in WMT20 [3.183845608678763]
This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised machine translation between German and Upper Sorbian.
In the fully unsupervised scenario, we achieved 25.5 and 23.7 BLEU translating from and into Upper Sorbian.
Our low-resource systems relied on transfer learning from German-Czech parallel data and achieved 57.4 BLEU and 56.1 BLEU.
arXiv Detail & Related papers (2020-10-22T14:04:01Z) - SJTU-NICT's Supervised and Unsupervised Neural Machine Translation
Systems for the WMT20 News Translation Task [111.91077204077817]
We participated in four translation directions of three language pairs: English-Chinese, English-Polish, and German-Upper Sorbian.
Based on different conditions of language pairs, we have experimented with diverse neural machine translation (NMT) techniques.
In our submissions, the primary systems won the first place on English to Chinese, Polish to English, and German to Upper Sorbian translation directions.
arXiv Detail & Related papers (2020-10-11T00:40:05Z) - Cross-lingual Supervision Improves Unsupervised Neural Machine
Translation [97.84871088440102]
We introduce a multilingual unsupervised NMT framework to leverage weakly supervised signals from high-resource language pairs to zero-resource translation directions.
Method significantly improves the translation quality by more than 3 BLEU score on six benchmark unsupervised translation directions.
arXiv Detail & Related papers (2020-04-07T05:46:49Z)
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.