ACL Findings2024
Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs
Masashi Oshika, Makoto Morishita, Tsutomu Hirao, Ryohei Sasano, Koichi Takeda
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
- An Interdisciplinary Approach to Human-Centered Machine TranslationMarine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli et al.EMNLP 2025 · 2 citations
- Toward Machine Interpreting: Lessons from Human Interpreting StudiesMatthias Sperber, Maureen de Seyssel, Jiajun Bao, Matthias PaulikEMNLP 2025 · 1 citation
Builds on3
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- COMET: A Neural Framework for MT EvaluationRicardo Rei, Craig Stewart, Ana C. Farinha, Alon LavieEMNLP 2020 · 6 citations
- Controlling Pre-trained Language Models for Grade-Specific Text SimplificationSweta Agrawal, Marine CarpuatEMNLP 2023 · 5 citations
Related papers
- On the Automatic Generation and Simplification of Children's StoriesMaria R. Valentini, Jennifer Weber, Jesus Salcido, Téa Wright et al.EMNLP 2023 · 7 citations
- Aligning Translation-Specific Understanding to General Understanding in Large Language ModelsYichong Huang, Baohang Li, Xiaocheng Feng, Wenshuai Huo et al.EMNLP 2024 · 7 citations
- Exploiting Target Language Data for Neural Machine Translation Beyond Back TranslationAbudurexiti Reheman, Yingfeng Luo, Junhao Ruan, Chunliang Zhang et al.ACL Findings 2024 · 1 citation
- Vocabulary Adaptation for Domain Adaptation in Neural Machine TranslationShoetsu Sato, Jin Sakuma, Naoki Yoshinaga, Masashi Toyoda et al.EMNLP Findings 2020 · 24 citations
- Enhancing Entertainment Translation for Indian Languages Using Adaptive Context, Style and LLMsPratik Rakesh Singh, Mohammadi Zaki, Pankaj WasnikAAAI 2025 · 2 citations
