RECORD
RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation
Computation and Language · Submitted 26 May 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our comprehensive experiments show that RAMP is a viable approach in both zero-shot and few-shot settings.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | 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. | gap 0.75 | 0.07 | 0.02 | asserted 0.99 |
| s2 | 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. | contribution 0.87 | 0.77 | 0.09 | asserted 0.99 |
| s3 | 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. | method 0.81 | 0.85 | 0.17 | asserted 1.00 |
| s4 | Our comprehensive experiments show that RAMP is a viable approach in both zero-shot and few-shot settings. | result 0.90 | 0.96 | 0.84 | asserted 0.98 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 4 sentences without a confident label
Uses the method or tool of 1 paper
-
For (2), we train multilingual classifiers on top of the mDeBERTa-v3 encoder [ref] .
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing · Evaluation Metrics · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.