| Challenge: | Existing adapter layers are more parameter-efficient and provide better performance than bilingual ones. |
| Approach: | They propose to use monolingual adapter layers instead of bilingual ones to compose them and generalize to unseen language pairs. |
| Outcome: | The proposed adapter layer formalism achieves a median improvement of +2.77 BLEU points over a 20-language multilingual Transformer baseline trained on TED talks. |
Similar Papers
Adapting to Non-Centered Languages for Zero-shot Multilingual Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies attributed zero-shot translation to domination of central language, e.g. English, but we supplement this viewpoint with the strict dependence of non-centered languages. |
| Approach: | They propose a language-specific modeling method that adapts to non-centered languages to counteract the instability of zero-shot translation. |
| Outcome: | The proposed method performs better than baselines in centered data conditions and can easily fit non-centered data. |
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to improve multilingual neural machine translation (NMT) are weak, and lack robustness to support language pairs with varying typological characteristics. |
| Approach: | They propose to deepen NMT models to support language pairs with varying typological characteristics by random online backtranslation. |
| Outcome: | The proposed approach narrows the performance gap with bilingual models and improves zero-shot performance by 10 BLEU, approaching conventional pivot-based methods. |
Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models do not differentiate between semantic and linguistic features, resulting in the entanglement of knowledge and linguistics within the model. |
| Approach: | They propose to exploit both semantic and linguistic features to enhance multilingual translation by disentangling encoder representations and integrating low-level linguistic encoders. |
| Outcome: | The proposed model improves zero-shot translation while maintaining performance in supervised translation on multilingual datasets. |
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual neural machine translation models perform poorly on language pairs with no parallel corpus. |
| Approach: | They propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data and preserves the model architecture without introducing parameters. |
| Outcome: | The proposed approach improves performance in translation directions where existing models are weak and mitigates degeneration in the well-performing translation directions, offering flexibility in the real-world scenario. |
A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that multilingual NMT models can handle more than one translation direction with a single system. |
| Approach: | They propose a multilingual neural machine translation model that can handle more than one translation direction with a single system. |
| Outcome: | The proposed model performs well in low-resource settings against bilingual systems. |
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual unsupervised machine translation is a computationally expensive and hard to tune approach . auxiliary parallel data is used to train translation systems from monolingual data . |
| Approach: | They propose to use auxiliary parallel language pairs to train unsupervised machine translations . they propose to add auxiliary languages to pre-trained mBART-50 models with denoising adapters . |
| Outcome: | The proposed approach is on-par with back-translation and allows adding unseen languages incrementally. |
LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing LT strategies cannot indicate the desired target language on zero-shot translation, i.e., the off-target issue. |
| Approach: | They propose a language converter strategy that embeds the target language into the top encoder layers to mitigate confusion in the encoder and ensures stable language indication for the decoder. |
| Outcome: | The proposed language converter strategy significantly mitigates off-target issue on multiUN, TED, and OPUS-100 datasets. |
Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mapping (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing model structure and training scheme cannot ensure universal representations and cross-mappings because of lacking explicit constraints. |
| Approach: | They propose a state mover’s distance model to model the difference of the representations output by the encoder and a agreement-based training scheme to minimize the proposed distance to learn universal representations. |
| Outcome: | The proposed model can translate between languages unseen during training, i.e., zero-shot translation. |
ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot cross-lingual transfer have focused on training with adapters of a single source and testing either with the target LA or LA of another related language. |
| Approach: | They propose to leverage LAs of multiple (linguistically or geographically related) source languages for more effective cross-lingual transfer instead of just one source LA . they extend their novel neural architecture, ZGUL, to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language . |
| Outcome: | Extensive experimentation across four language groups, covering 15 unseen target languages, shows improvements of up to 3.2 average F1 points over baselines on POS tagging and NER tasks. |
Improving Zero-Shot Translation by Disentangling Positional Information (2021.acl-long)
Copied to clipboard
| Challenge: | Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. |
| Approach: | They propose to remove residual connections in an encoder layer to reduce the difficulty of generalizing to new translation directions. |
| Outcome: | The proposed model outperforms pivot-based translation in terms of quality and ease of integration of new languages. |