# Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages

arXiv: https://arxiv.org/abs/1702.06135 · HTML: https://mlsanity.com/paper/1702.06135/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 10 of 10)

- [Contrastive Learning for Many-to-many Multilingual Neural Machine Translation](https://mlsanity.com/paper/2105.09501/) (2021)
- [Scaling Laws for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2302.09650/) (2023)
- [Back-translation for Large-Scale Multilingual Machine Translation](https://mlsanity.com/paper/2109.08712/) (2021)
- [Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2104.08478/) (2021)
- [YANMTT: Yet Another Neural Machine Translation Toolkit](https://mlsanity.com/paper/2108.11126/) (2021)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Checks and Strategies for Enabling Code-Switched Machine Translation](https://mlsanity.com/paper/2210.05096/) (2022)
- [Bilingual Synchronization: Restoring Translational Relationships with Editing Operations](https://mlsanity.com/paper/2210.13163/) (2022)
- [Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs](https://mlsanity.com/paper/2111.13284/) (2021)
- [Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems](https://mlsanity.com/paper/2503.07195/) (2025)

## Abstract (arXiv)

In this paper, we explore a simple solution to "Multi-Source Neural Machine Translation" (MSNMT) which only relies on preprocessing a N-way multilingual corpus without modifying the Neural Machine Translation (NMT) architecture or training procedure. We simply concatenate the source sentences to form a single long multi-source input sentence while keeping the target side sentence as it is and train an NMT system using this preprocessed corpus. We evaluate our method in resource poor as well as resource rich settings and show its effectiveness (up to 4 BLEU using 2 source languages and up to 6 BLEU using 5 source languages). We also compare against existing methods for MSNMT and show that our solution gives competitive results despite its simplicity. We also provide some insights on how the NMT system leverages multilingual information in such a scenario by visualizing attention.