arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.07249cs.CLcs.LGstat.ML
收藏

在CNN的单个单元中发现自然语言概念

Discovery of Natural Language Concepts in Individual Units of CNNs

Seoul National University(首尔国立大学);Kakao(Kakao公司);Kakao Brain(Kakao Brain研究院)

Seil Na, Yo Joong Choe, Dong-Hyun Lee, Gunhee Kim

摘要:

尽管深度卷积网络在许多自然语言任务中实现了性能的提高,但由于难以解释,它们一直被视为黑箱。特别是,很少有人知道它们如何在中间层表示语言。为了理解在语言任务上训练的深度卷积网络的表示,我们证明了单个单元对特定的词素、单词和短语有选择性地做出响应,而不是对任意和不可解释的模式做出响应。为了定量分析这种有趣的现象,我们提出了一种概念对齐方法的基础上如何单位响应复制文本。我们使用不同的架构对多个数据集进行分析,以执行分类和翻译任务,并为深入了解模型如何理解自然语言提供新的见解。

英文摘要:

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how they represent language in their intermediate layers. In an attempt to understand the representations of deep convolutional networks trained on language tasks, we show that individual units are selectively responsive to specific morphemes, words, and phrases, rather than responding to arbitrary and uninterpretable patterns. In order to quantitatively analyze such an intriguing phenomenon, we propose a concept alignment method based on how units respond to the replicated text. We conduct analyses with different architectures on multiple datasets for classification and translation tasks and provide new insights into how deep models understand natural language.

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。

↑