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 1901.01574cs.CL
收藏

短语表平滑中词汇缩减方法的比较研究

A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing

Human Language Technology and Pattern Recognition Group(人类语言技术与模式识别小组);RWTH Aachen University(亚琛工业大学);Lilt, Inc.(Lilt公司);Aachen, Germany((注:Aachen, Germany为地址,非机构,不应提取))

Yunsu Kim, Andreas Guta, Joern Wuebker, Hermann Ney

摘要:

本文系统地分析了词汇缩减对短语翻译模型的平滑效果。我们广泛地比较了各种单词级词汇表,表明平滑的性能不会受到词汇表选择的显着影响。这一结果提供了经验证据,表明标准短语翻译模型是非常稀疏的。我们的实验还表明,词汇减少是更有效的平滑大规模的短语表。

英文摘要:

This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models. We extensively compare various word-level vocabularies to show that the performance of smoothing is not significantly affected by the choice of vocabulary. This result provides empirical evidence that the standard phrase translation model is extremely sparse. Our experiments also reveal that vocabulary reduction is more effective for smoothing large-scale phrase tables.

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。

↑