arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.07046cs.CL
收藏

鲁棒语义角色标注的特征生成

Feature Generation for Robust Semantic Role Labeling

Human Language Technology Center of Excellence(人类语言技术卓越中心);Johns Hopkins University(约翰斯·霍普金斯大学)

Travis Wolfe, Mark Dredze, Benjamin Van Durme

摘要:

手工设计的特征集是创建健壮的NLP模型的一种很好理解的方法,但它们需要大量的专业知识和努力来创建。在这项工作中,我们描述了如何自动生成丰富的功能集从简单的单元称为featlets,需要较少的工程。使用信息增益来指导生成过程,我们在两个标准的语义角色标注数据集上训练训练模型,这些模型几乎没有任务或语言洞察力。

英文摘要:

Hand-engineered feature sets are a well understood method for creating robust NLP models, but they require a lot of expertise and effort to create. In this work we describe how to automatically generate rich feature sets from simple units called featlets, requiring less engineering. Using information gain to guide the generation process, we train models which rival the state of the art on two standard Semantic Role Labeling datasets with almost no task or linguistic insight.

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。

↑