Challenge: Using a single encoder and decoder for all directions is a popular scheme for multilingual NMT.
Approach: They propose a scheme that uses a single encoder and decoder for all directions . they show that enforcing sparsity and decorrelation on encoder intermediate representations mitigates this problem .
Outcome: The proposed model degenerates when decoding non-English texts into English regardless of the target specifier token.

Similar Papers

Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations (P19-1)

Copied to clipboard

Challenge: Existing approaches to train a multilingual NMT model for low-resource languages are lacking in terms of number of supervised examples.
Approach: They propose to use decoder pre-training and back-translation to solve the degeneracy problem by analyzing spurious correlations between source and decoded sentences.
Outcome: The proposed methods show significant improvement over the pivot-based approach on three challenging multilingual datasets.
Improving Multilingual Translation by Representation and Gradient Regularization (2021.emnlp-main)

Copied to clipboard

Challenge: Multilingual Neural Machine Translation models often produce low quality translations, often failing to produce outputs in the right target language.
Approach: They propose a joint approach to regularize NMT models at both representation-level and gradient-level to reduce off-target translation occurrences and improve zero-shot translation performance.
Outcome: The proposed approach reduces off-target translation occurrences and improves zero-shot translation performance by +5.59 and +10.38 BLEU on WMT and OPUS datasets.
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.
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to achieve zero-shot translation suffer from spurious correlations between output language and language invariant semantics.
Approach: They propose a method that denoizes the autoencoder objective based on pivot language into traditional training objective to improve translation accuracy on zero-shot directions.
Outcome: The proposed method eliminates spurious correlations and outperforms state-of-the-art methods on two benchmark machine translation datasets.
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 Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve zero-shot translation performance by learning language-agnostic representations and maximizing cross-lingual transfer have been proposed.
Approach: They propose a cross-lingual consistency regularization to bridge the representation gap between different languages and boost zero-shot translation performance.
Outcome: The proposed model improves translation performance on low-resource and high-res benchmarks and closes the sentence representation gap and aligns the representation space.
Modularized Multilingual NMT with Fine-grained Interlingua (2024.naacl-long)

Copied to clipboard

Challenge: Neural Machine Translation (MNMT) systems lack layer-sharing to generate interlingua features . however, layer-share structure does not guarantee explicit propagation of language-specific features to respective decoders.
Approach: They propose to share top of language-specific encoder layers to enable interlingua features . their method demonstrates an improved average BLEU score by "+2.90" in En-to-Any directions .
Outcome: The proposed approach improves the BLEU score by "+2.90" in En-to-Any directions and by "+1.06" in zero-shot translation.
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained multilingual language encoders do not precisely align words and phrases across languages.
Approach: They propose a learning strategy for training robust models by drawing connections between adversarial examples and failure cases of zero-shot cross-lingual transfer.
Outcome: The proposed model can achieve good performance even if representations of different languages are not aligned well.
Consistency by Agreement in Zero-Shot Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: In this paper, we focus on zero-shot generalization—a challenging setup that tests models on translation directions they have not been optimized for at training time.
Approach: They propose a method that allows for a consistent agreement-based training method that encourages the model to produce equivalent translations of parallel sentences in auxiliary languages.
Outcome: The proposed model improves on public zero-shot translation benchmarks without loss of performance on supervised translation directions.
Zero-Resource Neural Machine Translation with Monolingual Pivot Data (D19-56)

Copied to clipboard

Challenge: Neural machine translation systems have relied on large amounts of parallel training data between the source and target language.
Approach: They propose methods for generating pseudo-parallel corpora using pivot-language data . they use English as the pivot language to train the zero-shot system .
Outcome: The proposed methods improve the zero-shot neural machine translation system for a high-resource language pair using English as the pivot language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations