RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

Abstract

Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due to its usefulness in real-world applications, progress in the task is currently limited by dataset availability, since most prior approaches rely on supervised methods. To address this limitation, we propose Retrieval and Attribute-Marking enhanced Prompting (RAMP), which leverages large multilingual language models to perform ACT in few-shot and zero-shot settings. RAMP improves generation accuracy over the standard prompting approach by (1) incorporating a semantic similarity retrieval component for selecting similar in-context examples, and (2) marking in-context examples with attribute annotations. Our comprehensive experiments show that RAMP is a viable approach in both zero-shot and few-shot settings.

arXiv commentAccepted at ACL 2023

References in corpus (12)

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• PaLM: Scaling Language Modeling with Pathways
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
• Getting Gender Right in Neural Machine Translation
• Controlling the Output Length of Neural Machine Translation
• In-context Examples Selection for Machine Translation
• Prompting PaLM for Translation: Assessing Strategies and Performance
• Using natural language prompts for machine translation
• Towards Explainable Evaluation Metrics for Natural Language Generation
• Controlling Styles in Neural Machine Translation with Activation Prompt