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 2106.05426cs.CLcs.LG
收藏

语言表示空间中的低维结构反映在脑响应中

Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses

UT Austin(德克萨斯大学);Intel Labs(英特尔实验室)

Richard Antonello, Javier Turek, Vy Vo, Alexander Huth

AI总结:

研究揭示语言表示空间的低维结构,并通过fMRI验证其与大脑自然语言处理层次的关系。

摘要:

神经语言模型、翻译模型和语言标记任务所学习的表示之间有多大的相关性?我们通过将计算机视觉中的编码器-解码器迁移学习方法适应到语言任务中,来回答这个问题。该方法研究了从不同网络的隐藏表示中提取的100种不同特征空间之间的结构。这种方法揭示了一种低维结构,其中语言模型和翻译模型在词嵌入、语法和语义任务以及未来词嵌入之间平滑地插值。我们将这种低维结构称为语言表示嵌入,因为它编码了处理语言所需的各种NLP任务中表示之间的关系。我们发现,这种表示嵌入可以预测每个单独的特征空间映射到人类大脑对自然语言刺激的响应(通过fMRI记录)的程度。此外,我们发现这种结构的主维度可以用来创建一个指标,突出大脑的自然语言处理层次结构。这表明,这种嵌入捕捉了大脑部分自然语言表示结构。

英文摘要:

How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transfer learning method from computer vision to investigate the structure among 100 different feature spaces extracted from hidden representations of various networks trained on language tasks. This method reveals a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We call this low-dimensional structure a language representation embedding because it encodes the relationships between representations needed to process language for a variety of NLP tasks. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. Additionally, we find that the principal dimension of this structure can be used to create a metric which highlights the brain's natural language processing hierarchy. This suggests that the embedding captures some part of the brain's natural language representation structure.

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。

↑