Extreme Adaptation for Personalized Neural Machine Translation

Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.

• Publication year

  2018

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2018-05-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.18653/v1/P18-2050arXiv 1805.01817
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Continuous Learning from Human Post-Edits for Neural Machine Translation

  2017cited by this paper
• Instance Weighting for Neural Machine Translation Domain Adaptation

  2017cited by this paper
• DyNet: The Dynamic Neural Network Toolkit

  2017cited by this paper
• Regularization techniques for fine-tuning in neural machine translation

  2017cited by this paper
• Stronger Baselines for Trustable Results in Neural Machine Translation

  2017cited by this paper
• An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation

  2017cited by this paper
• Cost Weighting for Neural Machine Translation Domain Adaptation

  2017cited by this paper
• Personalized Machine Translation: Preserving Original Author Traits

  2016cited by this paper
• Controlling Politeness in Neural Machine Translation via Side Constraints

  2016influential reference
• Using the Output Embedding to Improve Language Models

  2016cited by this paper
• Transfer Learning for Low-Resource Neural Machine Translation

  2016cited by this paper
• One Sentence One Model for Neural Machine Translation

  2016cited by this paper
• Motivating Personality-aware Machine Translation

  2015cited by this paper
• Deep Unordered Composition Rivals Syntactic Methods for Text Classification

  2015influential reference
• Rethinking the Inception Architecture for Computer Vision

  2015influential reference
• Neural Machine Translation of Rare Words with Subword Units

  2015influential reference
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

  2015cited by this paper
• Stanford Neural Machine Translation Systems for Spoken Language Domains

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Intelligent Selection of Language Model Training Data

  2010cited by this paper
• Adaptive Development Data Selection for Log-linear Model in Statistical Machine Translation

  2010cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Statistical Significance Tests for Machine Translation Evaluation

  2004cited by this paper
• Improving Performance of Transfer-Driven Machine Translation with Extra-Linguistic Informatioon from Context, Situation and Environment

  1997cited by this paper
• International

  1964cited by this paper

• DKF: Domain knowledge fusion in progressive incremental learning for multi-domain machine translation

  2025cites this paper
• Steering Large Language Models for Machine Translation Personalization

  2025cites this paper
• A decade of gender bias in machine translation

  2025cites this paper
• Sustaining Human Agency, Attending to Its Cost: An Investigation into Generative AI Design for Non-Native Speakers' Language Use

  2025cites this paper
• JLMS25 and Jiao-Liao Mandarin Speech Recognition Based on Multi-Dialect Knowledge Transfer

  2025cites this paper
• Diverse Sign Language Translation

  2024cites this paper
• What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study

  2024cites this paper
• Evaluating Synthetic Data Generation from User Generated Text

  2024cites this paper
• Attribute-Based Injection Transformer for Personalized Sentiment Analysis

  2024cites this paper
• Enhancing sentiment and emotion translation of review text through MLM knowledge integration in NMT

  2024cites this paper
• Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback

  2023cites this paper
• Reference-less Analysis of Context Specificity in Translation with Personalised Language Models

  2023cites this paper
• Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation

  2023cites this paper
• Improved neural machine translation using Natural Language Processing (NLP)

  2023cites this paper
• How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?

  2023cites this paper
• Incorporating Human Translator Style into English-Turkish Literary Machine Translation

  2023cites this paper
• Pluggable Neural Machine Translation Models via Memory-augmented Adapters

  2023influential citation
• RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

  2023cites this paper
• MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation

  2023cites this paper
• Unified Model Learning for Various Neural Machine Translation

  2023cites this paper
• Tool Learning with Foundation Models

  2023cites this paper
• CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality

  2022cites this paper
• Controlling Styles in Neural Machine Translation with Activation Prompt

  2022cites this paper
• Building User-oriented Personalized Machine Translator based on User-Generated Textual Content

  2022cites this paper
• On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey

  2022cites this paper
• FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation

  2022cites this paper
• PePe: Personalized Post-editing Model utilizing User-generated Post-edits

  2022influential citation
• Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation

  2022cites this paper
• Improving Machine Translation Formality Control with Weakly-Labelled Data Augmentation and Post Editing Strategies

  2022cites this paper
• Prompt-Driven Neural Machine Translation

  2022influential citation
• Controlling Extra-Textual Attributes about Dialogue Participants: A Case Study of English-to-Polish Neural Machine Translation

  2022cites this paper
• A Personalized Cross-Platform Post Style Transfer Method Based on Transformer and Bi-Attention Mechanism

  2022cites this paper
• Personalized sentiment classification of customer reviews via an interactive attributes attention model

  2021cites this paper
• BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

  2021cites this paper
• Synthesizing Monolingual Data for Neural Machine Translation

  2021influential citation
• Revisiting Multi-Domain Machine Translation

  2021cites this paper
• Membership Inference Attacks on Machine Learning: A Survey

  2021cites this paper
• Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation

  2021cites this paper
• Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey

  2021cites this paper
• Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models

  2021cites this paper
• The practical ethics of bias reduction in machine translation: why domain adaptation is better than data debiasing

  2021cites this paper
• Towards Modeling the Style of Translators in Neural Machine Translation

  2021influential citation
• Continual Learning for Neural Machine Translation

  2021cites this paper
• Machine Translation Verbosity Control for Automatic Dubbing

  2021influential citation
• Towards User-Driven Neural Machine Translation

  2021cites this paper
• Towards Universality in Multilingual Text Rewriting

  2021cites this paper
• Attainable Text-to-Text Machine Translation vs. Translation: Issues Beyond Linguistic Processing

  2021cites this paper
• Augmenting Decompiler Output with Learned Variable Names and Types

  2021cites this paper
• Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer

  2021cites this paper
• Reinforced NMT for Sentiment and Content Preservation in Low-resource Scenario

  2021cites this paper
• Context-Aware Neural Machine Translation for Korean Honorific Expressions

  2021cites this paper
• On The Vulnerability of Recurrent Neural Networks to Membership Inference Attacks

  2021influential citation
• Learning Collections of Functions

  2021influential citation
• Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem

  2020cites this paper
• Meta-Learning for Few-Shot NMT Adaptation

  2020cites this paper
• On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation

  2020cites this paper
• On the Integration of Linguistic Features into Statistical and Neural Machine Translation

  2020cites this paper
• Machine Translation System Selection from Bandit Feedback

  2020cites this paper
• Neural Machine Translation

  2020cites this paper
• FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation

  2020cites this paper
• A Study of Residual Adapters for Multi-Domain Neural Machine Translation

  2020cites this paper
• Sprachvarietäten- abhängige Terminologie in der neuronalen maschinellen Übersetzung: Eine Analyse in der Sprachrichtung Englisch-Deutsch mit Schwerpunkt auf der österreichischen Varietät der deutschen Sprache

  2020cites this paper
• Factorized Transformer for Multi-Domain Neural Machine Translation

  2020cites this paper
• Distilling Multiple Domains for Neural Machine Translation

  2020cites this paper
• Personal Semantic Variations in Word Meanings: Induction, Application, and Analysis

  2020cites this paper
• Mitigating Gender Bias in Machine Translation with Target Gender Annotations

  2020cites this paper
• Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task

  2020cites this paper
• Case Study: Deontological Ethics in NLP

  2020cites this paper
• FDMT: A Benchmark Dataset for Fine-grained Domain Adaptation in Machine Translation

  2020cites this paper
• A Survey of Domain Adaptation for Machine Translation

  2020cites this paper
• Document-level Neural Machine Translation with Document Embeddings

  2019cites this paper
• Lexical Micro-adaptation for Neural Machine Translation

  2019cites this paper
• Measuring Immediate Adaptation Performance for Neural Machine Translation

  2019cites this paper
• Modeling Personal Biases in Language Use by Inducing Personalized Word Embeddings

  2019cites this paper
• Integrating and Evaluating Extra-linguistic Context in Neural Machine Translation First

  2019cites this paper
• Towards Knowledge-Based Personalized Product Description Generation in E-commerce

  2019cites this paper
• Context-Aware Learning for Neural Machine Translation

  2019cites this paper
• Controlling Formality and Style of Machine Translation Output Using AutoML

  2019cites this paper
• Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training

  2019cites this paper
• SANVis: Visual Analytics for Understanding Self-Attention Networks

  2019cites this paper
• Simple, Scalable Adaptation for Neural Machine Translation

  2019cites this paper
• Domain Adaptation for MT: A Study with Unknown and Out-of-Domain Tasks

  2019cites this paper
• Domain Adaptive Text Style Transfer

  2019cites this paper
• Rethinking Attribute Representation and Injection for Sentiment Classification

  2019cites this paper
• Towards Knowledge-Based Recommender Dialog System

  2019cites this paper
• On the use of prior and external knowledge in neural sequence models

  2019cites this paper
• START NMT STOP Yes Update parameters No Accept ? Yes No Request Feedback ? Keep / Delete / Substitute / Accept Generate partial translations Identify uncertain locations Ask feedback

  2019cites this paper
• Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation

  2019cites this paper
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation

  2019cites this paper
• Understanding Interpersonal Variations in Word Meanings via Review Target Identification

  2019cites this paper
• Controlling the Output Length of Neural Machine Translation

  2019cites this paper
• Document-level Neural Machine Translation with Inter-Sentence Attention

  2019cites this paper
• Guiding Variational Response Generator to Exploit Persona

  2019cites this paper
• Controlling Neural Machine Translation Formality with Synthetic Supervision

  2019cites this paper
• Encoding-Decoding Methods for Neural Machine Translation

  2019cites this paper
• Auditing Data Provenance in Text-Generation Models

  2018cites this paper
• Multi-Task Neural Models for Translating Between Styles Within and Across Languages

  2018cites this paper
• Findings of the Second Workshop on Neural Machine Translation and Generation

  2018cites this paper
• Contextual Parameter Generation for Universal Neural Machine Translation

  2018cites this paper
• MTNT: A Testbed for Machine Translation of Noisy Text

  2018cites this paper