# Triangular Architecture for Rare Language Translation

arXiv: https://arxiv.org/abs/1805.04813 · HTML: https://mlsanity.com/paper/1805.04813/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2018.

## Built on by (most cited first, 7 of 7)

- [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)
- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables](https://mlsanity.com/paper/2109.04705/) (2021)
- [Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization](https://mlsanity.com/paper/2305.07310/) (2023)
- [Triangular Bidword Generation for Sponsored Search Auction](https://mlsanity.com/paper/2101.11349/) (2021)
- [End-to-end Training and Decoding for Pivot-based Cascaded Translation Model](https://mlsanity.com/paper/2305.02261/) (2023)

## Abstract (arXiv)

Neural Machine Translation (NMT) performs poor on the low-resource language pair (X,Z), especially when Z is a rare language. By introducing another rich language Y, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data (Y,Z) (may be small) and (X,Y) (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, Z is taken as the intermediate latent variable, and translation models of Z are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of (X,Y). Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.