← Search

Nan Lin

5 accepted papers

2025

Discovering Semantic Subdimensions through Disentangled Conceptual Representations

EMNLP 2025

Understanding the core dimensions of conceptual semantics is fundamental to uncovering how meaning is organized in language and the brain. Existing approaches often rely on predefined semantic dimensions that offer only broad representations, overlooking finer conceptual distinctions. This paper pro

Cited by 0SourcePDFScholar
2022

Is the Brain Mechanism for Hierarchical Structure Building Universal Across Languages? An fMRI Study of Chinese and English

EMNLP 2022main

Evidence from psycholinguistic studies suggests that the human brain builds a hierarchical syntactic structure during language comprehension. However, it is still unknown whether the neural basis of such structures is universal across languages. In this paper, we first analyze the differences in lan…

Cited by 6SourcePDFScholar
2022

Manipulation Planning From Demonstration Via Goal-Conditioned Prior Action Primitive Decomposition and Alignment

RA-L 2022

Manipulation plays a vital role in robotics but is left unsolved. Recent work attempts to leverage the hierarchical structure of tasks via using action primitives. However, due to trajectory distribution shift, prior action primitives could hardly be adapted to new tasks. In this letter, we propose

Cited by 15SourceScholar
2022

Probing Word Syntactic Representations in the Brain by a Feature Elimination Method

AAAI 2022technical

Neuroimaging studies have identified multiple brain regions that are associated with semantic and syntactic processing when comprehending language. However, existing methods cannot explore the neural correlates of fine-grained word syntactic features, such as part-of-speech and dependency relations.…

Cited by 16SourcePDFScholar
2019

IMU-Based Active Safe Control of a Variable Stiffness Soft Actuator

RA-L 2019

Using soft pneumatic actuators is a feasible solution in the dynamic unstructed environment, thanks to their light weight and inherent compliance. It is commonly agreed that the passive compliance and adaptivity of soft robots make them much safer. However, under some special circumstances where str

Cited by 24SourceScholar