arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.04178cs.CL
收藏

为什么我们已经从建立成熟的分类法转向简单地检测上位关系

Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations

Sapienza University of Rome(罗马大学)

Jose Camacho-Collados

摘要:

在自然语言处理(NLP)文献中,分类法和上位关系的研究已经非常广泛。然而,传统的分类学习方法的评价一直是麻烦的,因为它主要依赖于ad-hoc实验,难以重现和人工昂贵。部分原因是,目前的研究最近一直集中在上位词检测任务。在本文中,我们反映了这一趋势,分析有关目前的评估程序的问题。最后,我们提出了未来工作的三个潜在途径,使基于它们的关系和资源在下游NLP应用中发挥更重要的作用。

英文摘要:

The study of taxonomies and hypernymy relations has been extensive on the Natural Language Processing (NLP) literature. However, the evaluation of taxonomy learning approaches has been traditionally troublesome, as it mainly relies on ad-hoc experiments which are hardly reproducible and manually expensive. Partly because of this, current research has been lately focusing on the hypernymy detection task. In this paper we reflect on this trend, analyzing issues related to current evaluation procedures. Finally, we propose three potential avenues for future work so that is-a relations and resources based on them play a more important role in downstream NLP applications.

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。

↑