# Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning

arXiv: https://arxiv.org/abs/2303.18011 · HTML: https://mlsanity.com/paper/2303.18011/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1604.02201/) (2016)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)
- [Contrastive Learning for Many-to-many Multilingual Neural Machine Translation](https://mlsanity.com/paper/2105.09501/) (2021)
- [Convolutional Neural Network Architectures for Matching Natural Language Sentences](https://mlsanity.com/paper/1503.03244/) (2015)
- [Fully Character-Level Neural Machine Translation without Explicit Segmentation](https://mlsanity.com/paper/1610.03017/) (2016)
- [Multilingual Neural Machine Translation with Language Clustering](https://mlsanity.com/paper/1908.09324/) (2019)
- [Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection](https://mlsanity.com/paper/1809.00068/) (2018)
- [Adversarial Neural Machine Translation](https://mlsanity.com/paper/1704.06933/) (2017)
- [Multilingual Neural Machine Translation With Soft Decoupled Encoding](https://mlsanity.com/paper/1902.03499/) (2019)
- [Multilingual NMT with a language-independent attention bridge](https://mlsanity.com/paper/1811.00498/) (2018)
- [Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data](https://mlsanity.com/paper/2105.15071/) (2021)
- [Revisiting Low Resource Status of Indian Languages in Machine Translation](https://mlsanity.com/paper/2008.04860/) (2020)
- [Improving Multilingual Neural Machine Translation For Low-Resource Languages: French,English - Vietnamese](https://mlsanity.com/paper/2012.08743/) (2020)

## Built on by (most cited first, 1 of 1)

- [Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation](https://mlsanity.com/paper/2409.00071/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GAN) offer a promising approach for Neural Machine Translation (NMT). However, feeding multiple morphologically languages into a single model during training reduces the NMT's performance. In GAN, similar to bilingual models, multilingual NMT only considers one reference translation for each sentence during model training. This single reference translation limits the GAN model from learning sufficient information about the source sentence representation. Thus, in this article, we propose Denoising Adversarial Auto-encoder-based Sentence Interpolation (DAASI) approach to perform sentence interpolation by learning the intermediate latent representation of the source and target sentences of multilingual language pairs. Apart from latent representation, we also use the Wasserstein-GAN approach for the multilingual NMT model by incorporating the model generated sentences of multiple languages for reward computation. This computed reward optimizes the performance of the GAN-based multilingual model in an effective manner. We demonstrate the experiments on low-resource language pairs and find that our approach outperforms the existing state-of-the-art approaches for multilingual NMT with a performance gain of up to 4 BLEU points. Moreover, we use our trained model on zero-shot language pairs under an unsupervised scenario and show the robustness of the proposed approach.