# Multi-Source Neural Machine Translation with Missing Data

arXiv: https://arxiv.org/abs/1806.02525 · HTML: https://mlsanity.com/paper/1806.02525/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2018.

## Built on by (most cited first, 8 of 8)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Alternative Input Signals Ease Transfer in Multilingual Machine Translation](https://mlsanity.com/paper/2110.07804/) (2021)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Automatic Document Sketching: Generating Drafts from Analogous Texts](https://mlsanity.com/paper/2106.07192/) (2021)
- [Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction](https://mlsanity.com/paper/2310.07487/) (2023)
- [NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs](https://mlsanity.com/paper/2511.07003/) (2025)
- [Transfer Learning for Sequence Generation: from Single-source to Multi-source](https://mlsanity.com/paper/2105.14809/) (2021)
- [How effective is Multi-source pivoting for Translation of Low Resource Indian Languages?](https://mlsanity.com/paper/2406.13332/) (2024)

## Abstract (arXiv)

Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an incomplete multilingual corpus in which some translations are missing. In practice, many multilingual corpora are not complete due to the difficulty to provide translations in all of the relevant languages (for example, in TED talks, most English talks only have subtitles for a small portion of the languages that TED supports). Existing studies on multi-source translation did not explicitly handle such situations. This study focuses on the use of incomplete multilingual corpora in multi-encoder NMT and mixture of NMT experts and examines a very simple implementation where missing source translations are replaced by a special symbol <NULL>. These methods allow us to use incomplete corpora both at training time and test time. In experiments with real incomplete multilingual corpora of TED Talks, the multi-source NMT with the <NULL> tokens achieved higher translation accuracies measured by BLEU than those by any one-to-one NMT systems.