Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation
Neural machine translation (NMT) systems amplify lexical biases present in their training data, leading to artificially impoverished language in output translations. These language-level characteristics render automatic translations different from text originally written in a language and human translations, which hinders their usefulness in for example creating evaluation datasets. Attempts to increase naturalness in NMT can fall short in terms of content preservation, where increased lexical diversity comes at the cost of translation accuracy. Inspired by the reinforcement learning from human feedback framework, we introduce a novel method that rewards both naturalness and content preservation. We experiment with multiple perspectives to produce more natural translations, aiming at reducing machine and human translationese. We evaluate our method on English-to-Dutch literary translation, and find that our best model produces translations that are lexically richer and exhibit more properties of human-written language, without loss in translation accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Single-Perspective Warps in Natural Image Stitching
Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but su…
Image StitchingExploring the Naturalness of AI-Generated Images
The proliferation of Artificial Intelligence-Generated Images (AGIs) has greatly expanded the Image Naturalness Assessment (INA) problem. Different from early definitions that mainly focus on tone-mapped images with limi…
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real world artifacts. In physical world attac…
Adversarial AttackAutonomous DrivingBenchmarkingUnified Prompt Attack Against Text-to-Image Generation Models
Text-to-Image (T2I) models have advanced significantly, but their growing popularity raises security concerns due to their potential to generate harmful images. To address these issues, we propose UPAM, a novel framework…
Image GenerationText to Image GenerationText-to-Image GenerationDo Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs
Current Large Language Models (LLMs) are predominantly designed with English as the primary language, and even the few that are multilingual tend to exhibit strong English-centric biases. Much like speakers who might pro…