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 2310.04460cs.CLcs.AI
收藏

聚焦神经编码:连接人类大脑与人工监督式语言表征

Tuning In to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language

KU Leuven(鲁汶大学);Chinese Academy of Sciences(中国科学院)

Jingyuan Sun, Xiaohan Zhang, Marie-Francine Moens

AI总结:

该研究针对中文语言神经编码研究空白,探究任务微调对预训练Transformer神经编码的影响,发现提示调优在多项任务上优于传统微调,细粒度概念实体处理任务的表征预测性最强,调参比例也会影响编码性能,为理解监督式人工与大脑语言表征的关联提供了依据。

摘要:

为理解支撑人类大脑语言表征的算法,过往研究尝试利用人工神经网络(ANN)生成的嵌入向量预测大脑对语言刺激的神经响应,这一过程被称为神经编码。但此类研究大多聚焦于使用无监督ANN探究英语等日耳曼语系语言的神经表征。本文旨在填补人类大脑与中文的监督式ANN表征之间的研究空白。具体而言,我们研究了任务微调如何影响用于神经编码的预训练Transformer,以及哪些任务能带来最优的编码性能。我们利用提示调优(prompt-tuning,一种在语言神经编码领域鲜少被探索的技术)在8项自然语言理解(NLU)任务上生成监督式表征。实验证明,在4项任务上,提示调优生成的表征相比传统微调能更好地预测大脑对中文刺激的神经响应。此外我们发现,需要对概念和实体进行细粒度处理的任务,其生成的表征对大脑激活模式的预测能力最强。我们还揭示,调优参数的比例会显著影响微调模型的神经编码性能。总体而言,我们的实验发现有助于更好地理解监督式人工语言表征与大脑语言表征之间的关联。

英文摘要:

To understand the algorithm that supports the human brain's language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a process known as neural encoding. However, most of these studies have focused on probing neural representations of Germanic languages, such as English, with unsupervised ANNs. In this paper, we propose to bridge the gap between human brain and supervised ANN representations of the Chinese language. Specifically, we investigate how task tuning influences a pretained Transformer for neural encoding and which tasks lead to the best encoding performances. We generate supervised representations on eight Natural Language Understanding (NLU) tasks using prompt-tuning, a technique that is seldom explored in neural encoding for language. We demonstrate that prompt-tuning yields representations that better predict neural responses to Chinese stimuli than traditional fine-tuning on four tasks. Furthermore, we discover that tasks that require a fine-grained processing of concepts and entities lead to representations that are most predictive of brain activation patterns. Additionally, we reveal that the proportion of tuned parameters highly influences the neural encoding performance of fine-tuned models. Overall, our experimental findings could help us better understand the relationship between supervised artificial and brain language 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。

↑