# Neural Machine Translation with Pivot Languages

arXiv: https://arxiv.org/abs/1611.04928 · HTML: https://mlsanity.com/paper/1611.04928/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2016.

## Built on by (most cited first, 25 of 25)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer](https://mlsanity.com/paper/2106.16171/) (2021)
- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Scaling Low-Resource MT via Synthetic Data Generation with LLMs](https://mlsanity.com/paper/2505.14423/) (2025)
- [UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation](https://mlsanity.com/paper/2207.04900/) (2022)
- [Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization](https://mlsanity.com/paper/2305.07310/) (2023)
- [MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation](https://mlsanity.com/paper/2208.08629/) (2022)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models](https://mlsanity.com/paper/2311.07439/) (2023)
- [AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT](https://mlsanity.com/paper/2106.05141/) (2021)
- [Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings](https://mlsanity.com/paper/2210.15851/) (2022)
- [An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog](https://mlsanity.com/paper/2109.12212/) (2021)
- [Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation](https://mlsanity.com/paper/2205.04067/) (2022)
- [Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda](https://mlsanity.com/paper/2505.02463/) (2025)
- [Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features](https://mlsanity.com/paper/2408.01394/) (2024)
- [Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation](https://mlsanity.com/paper/2412.19522/) (2024)
- [KD4MT: A Survey of Knowledge Distillation for Machine Translation](https://mlsanity.com/paper/2602.15845/) (2026)
- [ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language](https://mlsanity.com/paper/2408.08724/) (2024)
- [Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation](https://mlsanity.com/paper/2502.04537/) (2025)
- [Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer](https://mlsanity.com/paper/2109.12950/) (2021)
- [Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer](https://mlsanity.com/paper/2109.13097/) (2021)
- [End-to-end Training and Decoding for Pivot-based Cascaded Translation Model](https://mlsanity.com/paper/2305.02261/) (2023)
- [Direct Neural Machine Translation with Task-level Mixture of Experts models](https://mlsanity.com/paper/2310.12236/) (2023)

## Abstract (arXiv)

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.