面向塞内加尔沃洛夫语的低资源机器翻译
Low-Resourced Machine Translation for Senegalese Wolof Language
AI总结：
针对非洲沃洛夫语等低资源语言NLP发展滞后的问题，该研究构建了12.3万句对的沃洛夫语-法语平行语料，基于RNN开展不同配置的机器翻译实验，验证了子词数据、法英对训练的性能增益。
摘要：
近年来，自然语言处理（NLP）研究取得了长足进展，多项重大突破建立了新的基准。然而，这些进展主要惠及一类被称为资源丰富型的语言，例如英语和法语。大多数资源较匮乏的其他语言则被落在后面，包括沃洛夫语在内的大多数非洲语言便是如此。在本研究中，我们构建了一个包含12.3万句对的沃洛夫语/法语平行语料库，并基于循环神经网络（RNN）的机器翻译模型在不同数据配置下开展了实验。我们发现，在相同实验条件下，使用子词数据训练的模型，以及在法英语言对上训练的模型，其性能均优于在法-沃洛夫语对上训练的模型。
英文摘要：
Natural Language Processing (NLP) research has made great advancements in recent years with major breakthroughs that have established new benchmarks. However, these advances have mainly benefited a certain group of languages commonly referred to as resource-rich such as English and French. Majority of other languages with weaker resources are then left behind which is the case for most African languages including Wolof. In this work, we present a parallel Wolof/French corpus of 123,000 sentences on which we conducted experiments on machine translation models based on Recurrent Neural Networks (RNN) in different data configurations. We noted performance gains with the models trained on subworded data as well as those trained on the French-English language pair compared to those trained on the French-Wolof pair under the same experimental conditions.
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。
