Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that backtranslation improves UNMT performance by reducing the data gap between training and inference. |
| Approach: | They propose an online method to remedy the source discrepancy between training and inference . they use pseudo parallel data with translated source and translated target to mimic inference scenario . |
| Outcome: | The proposed method outperforms baselines on several widely-used language pairs by remedying the style and content gaps. |
Similar Papers
Improving Unsupervised Neural Machine Translation via Training Data Self-Correction (2024.lrec-main)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation models can generate mistakes during training . however, the quality of pseudo-parallel sentences cannot be guaranteed . |
| Approach: | They propose a method to improve the quality of pseudo-parallel sentences . they use token-level translations to correct mis-translated tokens . |
| Outcome: | Empirical results show that the proposed method outperforms baselines on widely used datasets. |
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods that use monolingual corpora for translation are not suitable for low-resource languages such as Estonian. |
| Approach: | They propose unsupervised neural machine translation (UNMT) that relies on monolingual corpora to train a robust UNMT system and improve its performance. |
| Outcome: | The proposed methods outperform conventional UNMT systems on several language pairs. |
Bridging the Gap between Training and Inference for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation generates target words sequentially while at inference it has to generate the entire sequence from scratch. |
| Approach: | They propose to use ground truth and inference to generate target words sequentially while at inference it has to generate the entire sequence from scratch. |
| Outcome: | Experiments on Chinese->English and WMT’14 English->German translation tasks show that the proposed model can achieve significant improvements on multiple datasets. |
Advances and Challenges in Unsupervised Neural Machine Translation (2021.eacl-tutorials)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation (UNMT) has achieved impressive results, but there are still several challenges for the technology. |
| Approach: | They present a framework for unsupervised neural machine translation (UNMT) they examine the latest progress and challenges of UNMT and examine how it holds up . |
| Outcome: | The proposed method has achieved impressive results but still faces challenges. |
Understanding Back-Translation at Scale (D18-1)
Copied to clipboard
| Challenge: | An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. |
| Approach: | They propose to augment parallel training corpus with back-translations of target language sentences to improve neural machine translation with monolingual data. |
| Outcome: | The proposed method achieves a state-of-the-art of 35 BLEU on the WMT’14 English-German test set. |
Exploiting Curriculum Learning in Unsupervised Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that the proposed method achieves consistent improvements with faster convergence speed. |
| Approach: | They propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. |
| Outcome: | The proposed method achieves consistent improvements with faster convergence speed on WMT 14 En-Fr, WMT14 En-De, and LDC En-Zh translation tasks. |
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation (P19-1)
Copied to clipboard
| Challenge: | Recent neural language generation systems often hallucinate contents when trained on loosely corresponding pairs of the input structure and text. |
| Approach: | They propose to integrate a language understanding module for data refinement with self-training iterations to induce strong equivalence between the input data and the paired text. |
| Outcome: | Experiments on the E2E challenge dataset show that the proposed framework reduces relative unaligned noise by 50% compared with the current state-of-the-art ensemble generator. |
Tagged Back-translation Revisited: Why Does It Really Work? (2020.acl-main)
Copied to clipboard
| Challenge: | In this paper, we show that neural machine translation systems trained on large back-translated data overfit some of the characteristics of machine-transcribed texts. |
| Approach: | They propose to add a tag to back-translations to help distinguish back-translated data from original parallel training data. |
| Outcome: | The proposed tag helps the system distinguish back-translated data from original parallel training data and is as effective as a tag in high-resource training. |
Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) uses a sequence-to-sequence model to generate synthetic data. |
| Approach: | They propose a method that adds synthetic data to sentences with high prediction loss during training and a variety of sampling strategies targeting difficult-to-predict words. |
| Outcome: | The proposed method improves translation quality by up to 1.7 and 1.2 Bleu points over back-translation using random sampling for German-English and English-German, respectively. |
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Unsupervised bilingual word embedding (UBWE) has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several language pairs. |
| Approach: | They propose two methods that train UNMT with UBWE agreement . they propose to use UBwe to initialize word embedding in UNMT . |
| Outcome: | The proposed methods outperform conventional methods on several language pairs. |