arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.04099cs.CLcs.LG
收藏

开发匈牙利语-英语的神经机器翻译模型

Developing neural machine translation models for Hungarian-English

Budapest University of Technology and Economics(布达佩斯技术与经济大学)

Attila Nagy

摘要:

我使用Hunglish 2语料库为英语-匈牙利语和匈牙利语-英语的神经机器翻译任务训练训练模型。这项工作的主要贡献是评估不同的数据增强方法在训练的NMT模型。我提出了5种不同的增强方法,它们是结构感知的,这意味着不是随机选择单词进行空白或替换,而是使用句子的依赖树作为增强的基础。论文首先对神经网络、序列建模、神经机器翻译、依存句法分析和数据增强等方面的研究进行了详细的文献综述。在对Hunglish 2语料库进行了详细的探索性数据分析和预处理之后,本文对所提出的数据增强技术进行了实验。匈牙利语-英语的最佳模型的BLEU得分为33.9,而英语-匈牙利语的最佳模型的BLEU得分为28.6。

英文摘要:

I train models for the task of neural machine translation for English-Hungarian and Hungarian-English, using the Hunglish2 corpus. The main contribution of this work is evaluating different data augmentation methods during the training of NMT models. I propose 5 different augmentation methods that are structure-aware, meaning that instead of randomly selecting words for blanking or replacement, the dependency tree of sentences is used as a basis for augmentation. I start my thesis with a detailed literature review on neural networks, sequential modeling, neural machine translation, dependency parsing and data augmentation. After a detailed exploratory data analysis and preprocessing of the Hunglish2 corpus, I perform experiments with the proposed data augmentation techniques. The best model for Hungarian-English achieves a BLEU score of 33.9, while the best model for English-Hungarian achieves a BLEU score of 28.6.

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。

↑