arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.00616cs.CL
收藏

阿拉伯语的语音依赖切分:在机器翻译和词性标注中的应用

Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging

Qatar Computing Research Institute – HBKU(卡塔尔计算研究所 – 哈马德·本·哈利法大学);MIT Computer Science and Artificial Intelligence Laboratory(麻省理工学院计算机科学与人工智能实验室)

Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali, Yonatan Belinkov, Stephan Vogel

摘要:

分词在改进任何阿拉伯语NLP应用程序中起着关键作用。因此,大量的研究已经花费在提高其准确性。然而,现成的工具是:i)使用复杂和ii)域/方言相关的。我们探索了三种独立于语言的形态分割方法:i)数据驱动的子词单元,ii)字符作为学习单元,iii)使用字符CNN(卷积神经网络)学习的词嵌入。在机器翻译和词性标注的任务中,我们发现这些方法可以实现接近,有时甚至超过最先进的性能。在我们的分析中,我们表明神经机器翻译系统对源和目标标记的比率很敏感,并且比率接近1或更大,给出了最佳性能。

英文摘要:

Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally surpass state-of-the-art performance. In our analysis, we show that a neural machine translation system is sensitive to the ratio of source and target tokens, and a ratio close to 1 or greater, gives optimal performance.

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。

↑