# Simultaneous Multi-Pivot Neural Machine Translation

arXiv: https://arxiv.org/abs/2104.07410 · HTML: https://mlsanity.com/paper/2104.07410/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 20 of 20)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://mlsanity.com/paper/1906.01181/) (2019)
- [Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation](https://mlsanity.com/paper/1806.03661/) (2018)
- [Zero-Resource Translation with Multi-Lingual Neural Machine Translation](https://mlsanity.com/paper/1606.04164/) (2016)
- [Multi-Source Neural Translation](https://mlsanity.com/paper/1601.00710/) (2016)
- [Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation](https://mlsanity.com/paper/1909.01559/) (2019)
- [Neural Machine Translation with Pivot Languages](https://mlsanity.com/paper/1611.04928/) (2016)
- [Simultaneous Translation with Flexible Policy via Restricted Imitation Learning](https://mlsanity.com/paper/1906.01135/) (2019)
- [Simultaneous Machine Translation with Visual Context](https://mlsanity.com/paper/2009.07310/) (2020)
- [Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages](https://mlsanity.com/paper/1702.06135/) (2017)
- [Speculative Beam Search for Simultaneous Translation](https://mlsanity.com/paper/1909.05421/) (2019)
- [Multi-Source Neural Machine Translation with Missing Data](https://mlsanity.com/paper/1806.02525/) (2018)
- [Opportunistic Decoding with Timely Correction for Simultaneous Translation](https://mlsanity.com/paper/2005.00675/) (2020)
- [Towards Multimodal Simultaneous Neural Machine Translation](https://mlsanity.com/paper/2004.03180/) (2020)
- [Multi-Source Syntactic Neural Machine Translation](https://mlsanity.com/paper/1808.10267/) (2018)

## Built on by (most cited first, 6 of 6)

- [Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer](https://mlsanity.com/paper/2106.16171/) (2021)
- [New Trends for Modern Machine Translation with Large Reasoning Models](https://mlsanity.com/paper/2503.10351/) (2025)
- [YANMTT: Yet Another Neural Machine Translation Toolkit](https://mlsanity.com/paper/2108.11126/) (2021)
- [Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models](https://mlsanity.com/paper/2311.07439/) (2023)
- [Robustness of Multi-Source MT to Transcription Errors](https://mlsanity.com/paper/2305.16894/) (2023)
- [MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation](https://mlsanity.com/paper/2210.00320/) (2022)

## Abstract (arXiv)

Parallel corpora are indispensable for training neural machine translation (NMT) models, and parallel corpora for most language pairs do not exist or are scarce. In such cases, pivot language NMT can be helpful where a pivot language is used such that there exist parallel corpora between the source and pivot and pivot and target languages. Naturally, the quality of pivot language translation is more inferior to what could be achieved with a direct parallel corpus of a reasonable size for that pair. In a real-time simultaneous translation setting, the quality of pivot language translation deteriorates even further given that the model has to output translations the moment a few source words become available. To solve this issue, we propose multi-pivot translation and apply it to a simultaneous translation setting involving pivot languages. Our approach involves simultaneously translating a source language into multiple pivots, which are then simultaneously translated together into the target language by leveraging multi-source NMT. Our experiments in a low-resource setting using the N-way parallel UN corpus for Arabic to English NMT via French and Spanish as pivots reveals that in a simultaneous pivot NMT setting, using two pivot languages can lead to an improvement of up to 5.8 BLEU.