arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04217cs.CL
收藏

简化面向儿童的翻译:利用大语言模型考虑习得年龄的迭代简化

Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs

Graduate School of Informatics, Nagoya University(名古屋大学信息学研究科);NTT Communication Science Laboratories, NTT Corporation(NTT株式会社NTT通信科学研究所)

Masashi Oshika, Makoto Morishita, Tsutomu Hirao, Ryohei Sasano, Koichi Takeda

AI总结:

本文提出利用大语言模型,根据词汇习得年龄迭代替换译文中的高难度词,以生成适合儿童理解水平的简化翻译,并在保持BLEU和COMET分数的同时有效降低词汇难度。

摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑