arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.06201cs.CL
收藏

神经语言模型的成分结构探讨

Probing for Constituency Structure in Neural Language Models

Qatar Computing Research Institute, Hamad Bin Khalifa University(哈马德·本·哈利法大学卡塔尔计算研究所)

David Arps, Younes Samih, Laura Kallmeyer, Hassan Sajjad

摘要:

在本文中,我们调查在何种程度上上下文神经语言模型(LM)隐式学习句法结构。更具体地说,我们专注于组成结构,在宾夕法尼亚州树库(PTB)。使用基于诊断分类器的标准探测技术,我们评估代表LM的神经元激活内的不同类别的成分的准确性,如RoberTa。为了确保我们的探测集中在句法知识而不是隐含的语义概括上,我们还对PTB版本进行了实验,该版本是通过在保持句法结构的同时随机替换成分而获得的,即,PTB的一个语义上格式错误但语法上格式正确的版本。我们发现,4个预训练的mathomer LM在我们的探测任务中获得了高性能,即使是在操纵的数据上,这表明它们表示中的语义和句法知识可以分离,并且选区信息实际上是由LM学习的。此外,我们表明,一个完整的选区树可以线性分离LM表示。

英文摘要:

In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly replacing constituents with each other while keeping syntactic structure, i.e., a semantically ill-formed but syntactically well-formed version of the PTB. We find that 4 pretrained transfomer LMs obtain high performance on our probing tasks even on manipulated data, suggesting that semantic and syntactic knowledge in their representations can be separated and that constituency information is in fact learned by the LM. Moreover, we show that a complete constituency tree can be linearly separated from LM representations.

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。

↑