# Pre-Translation for Neural Machine Translation

arXiv: https://arxiv.org/abs/1610.05243 · HTML: https://mlsanity.com/paper/1610.05243/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2016.

## Built on by (most cited first, 9 of 9)

- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing](https://mlsanity.com/paper/2310.14855/) (2023)
- [Continuous Learning in Neural Machine Translation using Bilingual Dictionaries](https://mlsanity.com/paper/2102.06558/) (2021)
- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)
- [Grounding Natural Language to SQL Translation with Data-Based Self-Explanations](https://mlsanity.com/paper/2411.02948/) (2024)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach](https://mlsanity.com/paper/2301.02071/) (2023)
- [Action based Network for Conversation Question Reformulation](https://mlsanity.com/paper/2111.14445/) (2021)

## Abstract (arXiv)

Recently, the development of neural machine translation (NMT) has significantly improved the translation quality of automatic machine translation. While most sentences are more accurate and fluent than translations by statistical machine translation (SMT)-based systems, in some cases, the NMT system produces translations that have a completely different meaning. This is especially the case when rare words occur. When using statistical machine translation, it has already been shown that significant gains can be achieved by simplifying the input in a preprocessing step. A commonly used example is the pre-reordering approach. In this work, we used phrase-based machine translation to pre-translate the input into the target language. Then a neural machine translation system generates the final hypothesis using the pre-translation. Thereby, we use either only the output of the phrase-based machine translation (PBMT) system or a combination of the PBMT output and the source sentence. We evaluate the technique on the English to German translation task. Using this approach we are able to outperform the PBMT system as well as the baseline neural MT system by up to 2 BLEU points. We analyzed the influence of the quality of the initial system on the final result.