用RNN+迁移学习提升英语到伊博语翻译效果
Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo
- 结合RNN与注意力机制，构建低资源语言翻译模型
- 迁移学习使性能提升4.83 BLEU点，达70%准确率
- 适合关注非洲低资源语言技术落地的研究者
本研究针对英语到伊博语这一低资源非洲语言（使用者超4000万）开发神经机器翻译（NMT）与基于Transformer的迁移学习模型。模型在经母语专家验证的圣经语料、本地新闻、维基百科及Common Crawl数据集上训练。采用带注意力机制的循环神经网络（包括LSTM和GRU）架构，并在SimpleTransformers框架中使用MarianNMT预训练模型进行迁移学习。RNN系统表现接近现有英伊博语基准。引入迁移学习后，性能提升4.83 BLEU点，翻译准确率估计达70%。结果表明，结合RNN与迁移学习可有效缩小低资源语言翻译性能差距。
原文摘要 · Abstract (English)
In this study, we develop Neural Machine Translation (NMT) and Transformer-based transfer learning models for English-to-Igbo translation - a low-resource African language spoken by over 40 million people across Nigeria and West Africa. Our models are trained on a curated and benchmarked dataset compiled from Bible corpora, local news, Wikipedia articles, and Common Crawl, all verified by native language experts. We leverage Recurrent Neural Network (RNN) architectures, including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), enhanced with attention mechanisms to improve translation accuracy. To further enhance performance, we apply transfer learning using MarianNMT pre-trained models within the SimpleTransformers framework. Our RNN-based system achieves competitive results, closely matching existing English-Igbo benchmarks. With transfer learning, we observe a performance gain of +4.83 BLEU points, reaching an estimated translation accuracy of 70%. These findings highlight the effectiveness of combining RNNs with transfer learning to address the performance gap in low-resource language translation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。