# Controlling Styles in Neural Machine Translation with Activation Prompt

arXiv: https://arxiv.org/abs/2212.08909 · HTML: https://mlsanity.com/paper/2212.08909/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 17 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [WARP: Word-level Adversarial ReProgramming](https://mlsanity.com/paper/2101.00121/) (2021)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data](https://mlsanity.com/paper/2203.08773/) (2022)
- [Personalized Machine Translation: Preserving Original Author Traits](https://mlsanity.com/paper/1610.05461/) (2016)
- [Rethinking Document-level Neural Machine Translation](https://mlsanity.com/paper/2010.08961/) (2020)
- [Extreme Adaptation for Personalized Neural Machine Translation](https://mlsanity.com/paper/1805.01817/) (2018)
- [Adapting Language Models for Non-Parallel Author-Stylized Rewriting](https://mlsanity.com/paper/1909.09962/) (2019)
- [NeurST: Neural Speech Translation Toolkit](https://mlsanity.com/paper/2012.10018/) (2020)
- [Controlling Neural Machine Translation Formality with Synthetic Supervision](https://mlsanity.com/paper/1911.08706/) (2019)
- [Generating Diverse Translation by Manipulating Multi-Head Attention](https://mlsanity.com/paper/1911.09333/) (2019)
- [Generating Diverse Translation from Model Distribution with Dropout](https://mlsanity.com/paper/2010.08178/) (2020)
- [Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts](https://mlsanity.com/paper/2209.11409/) (2022)

## Built on by (most cited first, 7 of 7)

- [A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models](https://mlsanity.com/paper/2305.01181/) (2023)
- [New Trends for Modern Machine Translation with Large Reasoning Models](https://mlsanity.com/paper/2503.10351/) (2025)
- [Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation](https://mlsanity.com/paper/2304.11501/) (2023)
- [RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation](https://mlsanity.com/paper/2305.17131/) (2023)
- [Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation](https://mlsanity.com/paper/2212.10313/) (2022)
- [How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?](https://mlsanity.com/paper/2309.08565/) (2023)
- [Incorporating Human Translator Style into English-Turkish Literary Machine Translation](https://mlsanity.com/paper/2307.11457/) (2023)

## Abstract (arXiv)

Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience. Earlier studies on this topic typically concentrate on regulating the level of formality and achieve some progress in this area. However, they still encounter two major challenges. The first is the difficulty in style evaluation. The style comprises various aspects such as lexis, syntax, and others that provide abundant information. Nevertheless, only formality has been thoroughly investigated. The second challenge involves excessive dependence on incremental adjustments, particularly when new styles are necessary. To address both challenges, this paper presents a new benchmark and approach. A multiway stylized machine translation (MSMT) benchmark is introduced, incorporating diverse categories of styles across four linguistic domains. Then, we propose a method named style activation prompt (StyleAP) by retrieving prompts from stylized monolingual corpus, which does not require extra fine-tuning. Experiments show that StyleAP could effectively control the style of translation and achieve remarkable performance.