arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.04315cs.CL
收藏

语言系统性初探

Probing Linguistic Systematicity

Department of Linguistics(语言学系);Quebec Artificial Intelligence Institute (Mila)(魁北克人工智能研究所 (Mila));School of Computer Science, McGill University(麦吉尔大学计算机科学学院);Facebook AI Research (FAIR)(Facebook 人工智能研究院 (FAIR));CIFAR AI Chair, Mila(CIFAR 人工智能讲席教授,Mila)

Emily Goodwin, Koustuv Sinha, Timothy J. O'Donnell

摘要:

最近,人们对深度自然语言理解模型是否表现出系统性的问题产生了很大的兴趣;泛化使得像单词这样的单元对它们出现的句子的意义做出一致的贡献。越来越多的证据表明,神经模型通常会非系统地泛化。我们从语言学的角度研究了系统性的概念,定义了一组探针和一组度量系统行为的指标。我们还确定了网络架构可以非系统地泛化的方式,并讨论了为什么这种形式的泛化可能不令人满意。作为一个案例研究,我们进行了一系列的实验中设置的自然语言推理(NLI),表明一些NLU系统实现高的整体性能,尽管是非系统的。

英文摘要:

Recently, there has been much interest in the question of whether deep natural language understanding models exhibit systematicity; generalizing such that units like words make consistent contributions to the meaning of the sentences in which they appear. There is accumulating evidence that neural models often generalize non-systematically. We examined the notion of systematicity from a linguistic perspective, defining a set of probes and a set of metrics to measure systematic behaviour. We also identified ways in which network architectures can generalize non-systematically, and discuss why such forms of generalization may be unsatisfying. As a case study, we performed a series of experiments in the setting of natural language inference (NLI), demonstrating that some NLU systems achieve high overall performance despite being non-systematic.

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。

↑