mlsanityData to 7 Oct 2026

Controlling Translation Formality Using Pre-trained Multilingual Language Models

arXiv 2205.06644 ↗First posted 13 May 2022cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper describes the University of Maryland's submission to the Special Task on Formality Control for Spoken Language Translation at iwslt, which evaluates translation from English into 6 languages with diverse grammatical formality markers. We investigate to what extent this problem can be addressed with a textitsingle multilingual model, simultaneously controlling its output for target language and formality. Results show that this strategy can approach the translation quality and formality control achieved by dedicated translation models. However, the nature of the underlying pre-trained language model and of the finetuning samples greatly impact results.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 13 May 2022.

Builds on

17 of 33 references.

References · 17

  1. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  2. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  3. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  4. 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 221
  5. 2019CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBcited by 177
  6. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  7. 2016Personalized Machine Translation: Preserving Original Author Traitscited by 47
  8. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 39
  9. 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
  10. 2019Controlling Text Complexity in Neural Machine Translationcited by 32
  11. 2021Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitutioncited by 31
  12. 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formalitycited by 24
5 more
  1. 2021Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfercited by 23
  2. 2019JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpuscited by 21
  3. 2021Few-shot Controllable Style Transfer for Low-Resource Multilingual Settingscited by 20
  4. 2019Controlling Neural Machine Translation Formality with Synthetic Supervisioncited by 18
  5. 2017JESC: Japanese-English Subtitle Corpuscited by 16

Built on by

Cited by year

Citing papers per year: 2023: 8; 2024: 2; 2025: 4.

14 papers.

Sort:

By area:

  1. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  2. 2024The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilitiescited by 22
  3. 2023Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interactioncited by 16
  4. 2025An Interdisciplinary Approach to Human-Centered Machine Translationcited by 6
  5. 2025Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMscited by 6
  6. 2025Towards Style Alignment in Cross-Cultural Translationcited by 4
  7. 2023In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languagescited by 2
  8. 2023MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translationcited by 2
  9. 2023How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?cited by 2
  10. 2023Comparing Styles across Languages: A Cross-Cultural Exploration of Politenesscited by 2
  11. 2024On Instruction-Finetuning Neural Machine Translation Modelscited by 2
  12. 2023Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generationcited by 0
2 more
  1. 2023Machine Translation to Control Formality Features in the Target Languagecited by 0
  2. 2025When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Contentcited by 0