近年来,神经机器翻译(NMT)已在日常生活中得到广泛应用。然而,当前的NMT缺乏一种机制来调整译文的难度水平,以匹配用户的语言水平。此外,由于NMT训练数据中的偏差,简单源句的译文往往使用了复杂的词汇。特别是,这可能对儿童构成问题,他们可能无法正确理解译文的含义。在本研究中,我们提出了一种方法,将译文中习得年龄(Age of Acquisition,AoA)较高的词替换为更简单的词,以使译文与用户水平相匹配。我们通过使用大语言模型(LLMs)来实现这一目标,向其提供由源句、译文和待替换目标词组成的三元组。我们利用简单英语维基百科上的回译方法构建了一个基准数据集。基于该数据集获得的实验结果表明,我们的方法能够有效地将高AoA词替换为低AoA词,并且能够迭代地替换大多数高AoA词,同时仍保持较高的BLEU和COMET分数。
英文摘要:
In recent years, neural machine translation (NMT) has been widely used in everyday life. However, the current NMT lacks a mechanism to adjust the difficulty level of translations to match the user's language level. Additionally, due to the bias in the training data for NMT, translations of simple source sentences are often produced with complex words. In particular, this could pose a problem for children, who may not be able to understand the meaning of the translations correctly. In this study, we propose a method that replaces words with high Age of Acquisitions (AoA) in translations with simpler words to match the translations to the user's level. We achieve this by using large language models (LLMs), providing a triple of a source sentence, a translation, and a target word to be replaced. We create a benchmark dataset using back-translation on Simple English Wikipedia. The experimental results obtained from the dataset show that our method effectively replaces high-AoA words with lower-AoA words and, moreover, can iteratively replace most of the high-AoA words while still maintaining high BLEU and COMET scores.
Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification
Department of Computer Science, School of Information Science and Technology, Guangdong University of Foreign Studies(计算机科学系,信息科学与技术学院,广东外语外贸大学);College of Intelligence and Computing, Tianjin University(智能与计算学院,天津大学);Lionrock AI Lab, China Merchants Research Institute of Advanced Technology(Lionrock AI实验室,中国远洋科技研究院)
UM_FHS at the CLEF 2025 SimpleText Track: Comparing No-Context and Fine-Tune Approaches for GPT-4.1 Models in Sentence and Document-Level Text Simplification
University of Maribor, Faculty of Health Science(马里博大学健康科学学院);University of Ljubljana, Faculty of Medicine(卢布尔雅那大学医学院);University of Edinburgh, Usher Institute(爱丁堡大学usher研究所)