# SYSTRAN's Pure Neural Machine Translation Systems

arXiv: https://arxiv.org/abs/1610.05540 · HTML: https://mlsanity.com/paper/1610.05540/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2016.

## Built on by (most cited first, 24 of 24)

- [General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining](https://mlsanity.com/paper/2203.10929/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models](https://mlsanity.com/paper/2305.01181/) (2023)
- [Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future](https://mlsanity.com/paper/2108.04543/) (2021)
- [Encouraging Neural Machine Translation to Satisfy Terminology Constraints](https://mlsanity.com/paper/2106.03730/) (2021)
- [Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021](https://mlsanity.com/paper/2403.01196/) (2024)
- [Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging](https://mlsanity.com/paper/2102.10160/) (2021)
- [End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages](https://mlsanity.com/paper/2106.12398/) (2021)
- [Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction](https://mlsanity.com/paper/2105.05498/) (2021)
- [Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints](https://mlsanity.com/paper/2204.13355/) (2022)
- [Language Modelling Approaches to Adaptive Machine Translation](https://mlsanity.com/paper/2401.14559/) (2024)
- [Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models](https://mlsanity.com/paper/2507.18263/) (2025)
- [CUNI systems for WMT21: Terminology translation Shared Task](https://mlsanity.com/paper/2109.09350/) (2021)
- [Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared task](https://mlsanity.com/paper/2111.02120/) (2021)
- [Translate-and-Revise: Boosting Large Language Models for Constrained Translation](https://mlsanity.com/paper/2407.13164/) (2024)
- [Modeling Target-side Inflection in Placeholder Translation](https://mlsanity.com/paper/2107.00334/) (2021)
- [Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding](https://mlsanity.com/paper/2204.00871/) (2022)
- [Disambiguated Lexically Constrained Neural Machine Translation](https://mlsanity.com/paper/2305.17351/) (2023)
- [Negative Lexical Constraints in Neural Machine Translation](https://mlsanity.com/paper/2308.03601/) (2023)
- [Analyzing Architectures for Neural Machine Translation Using Low Computational Resources](https://mlsanity.com/paper/2111.03813/) (2021)
- [A Template-based Method for Constrained Neural Machine Translation](https://mlsanity.com/paper/2205.11255/) (2022)
- [Knowledge Based Template Machine Translation In Low-Resource Setting](https://mlsanity.com/paper/2209.03554/) (2022)
- [Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System](https://mlsanity.com/paper/2508.18701/) (2025)
- [From Zero to Hero: An Open LLM Ecosystem for Armenian](https://mlsanity.com/paper/2609.03350/) (2026)

## Abstract (arXiv)

Since the first online demonstration of Neural Machine Translation (NMT) by LISA, NMT development has recently moved from laboratory to production systems as demonstrated by several entities announcing roll-out of NMT engines to replace their existing technologies. NMT systems have a large number of training configurations and the training process of such systems is usually very long, often a few weeks, so role of experimentation is critical and important to share. In this work, we present our approach to production-ready systems simultaneously with release of online demonstrators covering a large variety of languages (12 languages, for 32 language pairs). We explore different practical choices: an efficient and evolutive open-source framework; data preparation; network architecture; additional implemented features; tuning for production; etc. We discuss about evaluation methodology, present our first findings and we finally outline further work. Our ultimate goal is to share our expertise to build competitive production systems for "generic" translation. We aim at contributing to set up a collaborative framework to speed-up adoption of the technology, foster further research efforts and enable the delivery and adoption to/by industry of use-case specific engines integrated in real production workflows. Mastering of the technology would allow us to build translation engines suited for particular needs, outperforming current simplest/uniform systems.