When and Why is Unsupervised Neural Machine Translation Useless?

• URL: http://arxiv.org/abs/2004.10581v1
• Date: Wed, 22 Apr 2020 14:00:55 GMT
• Title: When and Why is Unsupervised Neural Machine Translation Useless?
• Authors: Yunsu Kim, Miguel Gra\c{c}a, Hermann Ney
• Abstract summary: In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised methods fail to produce reasonable translations. Our analyses pinpoint the limits of the current unsupervised NMT and also suggest immediate research directions.
• Score: 43.68079166777282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised methods fail to produce reasonable translations. We show that their performance is severely affected by linguistic dissimilarity and domain mismatch between source and target monolingual data. Such conditions are common for low-resource language pairs, where unsupervised learning works poorly. In all of our experiments, supervised and semi-supervised baselines with 50k-sentence bilingual data outperform the best unsupervised results. Our analyses pinpoint the limits of the current unsupervised NMT and also suggest immediate research directions.

Related papers

• Towards Effective Disambiguation for Machine Translation with Large Language Models [65.80775710657672]
  We study the capabilities of large language models to translate "ambiguous sentences" Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions.
  arXiv  Detail & Related papers  (2023-09-20T22:22:52Z)
• Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation [70.33052952571884]
  We propose to build a cascaded speech translation system without leveraging any kind of paired data. We use fully unpaired data to train our unsupervised systems and evaluate our results on CoVoST 2 and CVSS.
  arXiv  Detail & Related papers  (2023-05-12T13:07:51Z)
• Improving Multilingual Translation by Representation and Gradient Regularization [82.42760103045083]
  We propose a joint approach to regularize NMT models at both representation-level and gradient-level. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance.
  arXiv  Detail & Related papers  (2021-09-10T10:52:21Z)
• What Can Unsupervised Machine Translation Contribute to High-Resource Language Pairs? [18.924296648372795]
  We compare the style of correct translations generated by either supervised or unsupervised MT. We demonstrate a way to combine the benefits of unsupervised and supervised MT into a single system.
  arXiv  Detail & Related papers  (2021-06-30T05:44:05Z)
• Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translation [1.2891210250935146]
  This work focuses on comparing different solutions for machine translation on low resource language pairs. We discuss how the data size affects the performance of both unsupervised MT and transfer learning.
  arXiv  Detail & Related papers  (2021-03-31T20:47:19Z)
• When Does Unsupervised Machine Translation Work? [23.690875724726908]
  We conduct an empirical evaluation of unsupervised machine translation (MT) using dissimilar language pairs, dissimilar domains, diverse datasets, and authentic low-resource languages. We find that performance rapidly deteriorates when source and target corpora are from different domains. We additionally find that unsupervised MT performance declines when source and target languages use different scripts, and observe very poor performance on authentic low-resource language pairs.
  arXiv  Detail & Related papers  (2020-04-12T00:57:47Z)
• Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios [61.88012735215636]
  Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. In real-world scenarios, massive monolingual corpora do not exist for some extremely low-resource languages such as Estonian. We propose UNMT self-training mechanisms to train a robust UNMT system and improve its performance.
  arXiv  Detail & Related papers  (2020-04-09T12:07:17Z)
• 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.