arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.14575cs.CLcs.AI
收藏

为什么强大的自然语言理解是一个挑战

Why Robust Natural Language Understanding is a Challenge

Heriot-Watt University(赫瑞-瓦特大学);University of Edinburgh(爱丁堡大学);University of Strathclyde(思克莱德大学)

Marco Casadio, Ekaterina Komendantskaya, Verena Rieser, Matthew L. Daggitt, Daniel Kienitz, Luca Arnaboldi, Wen Kokke

摘要:

随着深度机器学习在现实生活中的应用,这项技术的一个特殊属性引起了人们的注意:鲁棒性神经网络众所周知的低鲁棒性,并且对小的输入扰动高度敏感。近年来,人们提出了许多检验网络鲁棒性的方法,但这些方法主要应用于计算机视觉。在本文中,我们提出了一个验证规范的自然语言理解分类的基础上更大的区域的利益,我们讨论了这样的任务的挑战。我们观察到,虽然数据几乎是线性可分的,验证者的斗争,输出积极的结果,我们解释的问题和影响。

英文摘要:

With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive to small input perturbations. Recently, many methods for verifying networks' general properties of robustness have been proposed, but they are mostly applied in Computer Vision. In this paper we propose a Verification specification for Natural Language Understanding classification based on larger regions of interest, and we discuss the challenges of such task. We observe that, although the data is almost linearly separable, the verifier struggles to output positive results and we explain the problems and implications.

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。

↑