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 1808.09055cs.CL
收藏

相关语言的依赖关系解析器之间的参数共享

Parameter sharing between dependency parsers for related languages

Uppsala University(乌普萨拉大学);University of Copenhagen(哥本哈根大学)

Miryam de Lhoneux, Johannes Bjerva, Isabelle Augenstein, Anders Søgaard

摘要:

以前的工作表明,相关语言的基于转换的神经依赖解析器之间的参数共享可以带来更好的性能,但对于共享什么参数没有共识。我们提出了一个评估的27个不同的参数共享策略在10种语言,代表五对相关的语言,每对来自不同的语言家族。我们发现,共享转换分类器参数总是有帮助的,而共享单词和/或字符LSTM参数的有用性各不相同。基于这一结果,我们提出了一个架构,其中的过渡分类器是共享的,和共享的字和字符参数控制的参数,可以调整验证数据。该模型是语言动机,并获得了显着的改进,单语训练的基线。我们还发现,共享转换分类器参数有助于在不相关的语言对上训练解析器,但我们发现,在不相关的语言的情况下,共享太多的参数没有帮助。

英文摘要:

Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to better performance, but there is no consensus on what parameters to share. We present an evaluation of 27 different parameter sharing strategies across 10 languages, representing five pairs of related languages, each pair from a different language family. We find that sharing transition classifier parameters always helps, whereas the usefulness of sharing word and/or character LSTM parameters varies. Based on this result, we propose an architecture where the transition classifier is shared, and the sharing of word and character parameters is controlled by a parameter that can be tuned on validation data. This model is linguistically motivated and obtains significant improvements over a monolingually trained baseline. We also find that sharing transition classifier parameters helps when training a parser on unrelated language pairs, but we find that, in the case of unrelated languages, sharing too many parameters does not help.

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。

↑