# Controlling Neural Machine Translation Formality with Synthetic Supervision

arXiv: https://arxiv.org/abs/1911.08706 · HTML: https://mlsanity.com/paper/1911.08706/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 18 of 18)

- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [How to Design Translation Prompts for ChatGPT: An Empirical Study](https://mlsanity.com/paper/2304.02182/) (2023)
- [CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality](https://mlsanity.com/paper/2205.04022/) (2022)
- [Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings](https://mlsanity.com/paper/2110.07385/) (2021)
- [A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models](https://mlsanity.com/paper/2305.01181/) (2023)
- [Isometric MT: Neural Machine Translation for Automatic Dubbing](https://mlsanity.com/paper/2112.08682/) (2021)
- [Controlling Translation Formality Using Pre-trained Multilingual Language Models](https://mlsanity.com/paper/2205.06644/) (2022)
- [RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation](https://mlsanity.com/paper/2305.17131/) (2023)
- [Controlling Styles in Neural Machine Translation with Activation Prompt](https://mlsanity.com/paper/2212.08909/) (2022)
- [Specification-Aware Machine Translation and Evaluation for Purpose Alignment](https://mlsanity.com/paper/2509.17559/) (2025)
- [Controlling Extra-Textual Attributes about Dialogue Participants -- A Case Study of English-to-Polish Neural Machine Translation](https://mlsanity.com/paper/2205.04747/) (2022)
- [One Source, Two Targets: Challenges and Rewards of Dual Decoding](https://mlsanity.com/paper/2109.10197/) (2021)
- [In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages](https://mlsanity.com/paper/2302.12299/) (2023)
- [Can Synthetic Translations Improve Bitext Quality?](https://mlsanity.com/paper/2203.07643/) (2022)
- [Pluggable Neural Machine Translation Models via Memory-augmented Adapters](https://mlsanity.com/paper/2307.06029/) (2023)
- [FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes](https://mlsanity.com/paper/2405.11942/) (2024)
- [Machine Translation to Control Formality Features in the Target Language](https://mlsanity.com/paper/2311.13475/) (2023)
- [When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content](https://mlsanity.com/paper/2512.17738/) (2025)

## Abstract (arXiv)

This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. Framing this problem as a neural sequence-to-sequence task ideally requires training triplets consisting of a bilingual sentence pair labeled with target language formality. However, in practice, available training examples are limited to English sentence pairs of different styles, and bilingual parallel sentences of unknown formality. We introduce a novel training scheme for multi-task models that automatically generates synthetic training triplets by inferring the missing element on the fly, thus enabling end-to-end training. Comprehensive automatic and human assessments show that our best model outperforms existing models by producing translations that better match desired formality levels while preserving the source meaning.