Work

Higher-order Comparisons of Sentence Encoder Representations

Year: 2019

Type: article

Abstract: Representational Similarity Analysis (RSA) is a technique developed by neuroscientists for comparing activity patterns of different measurement modalities (e.g., fMRI, electrophysiology, behavior). As a framework, RSA has several advantages over existing approaches to interpretation of language encoders based on probing or diagnostic classification: namely, it does not require large training samples, is not prone to overfitting, and it enables a more transparent comparison between the representational geometries of different models and modalities. We demonstrate the utility of RSA by establishing a previously unknown correspondence between widely-employed pretrained language encoders and human processing difficulty via eye-tracking data, showcasing its potential in the interpretability toolbox for neural models.

Source: Research at the University of Copenhagen (University of Copenhagen)

Authors: vqc439, vqc439, Kulmizev, Artur, Hill, Felix, Low, Daniel M. Low, Søgaard, Anders

Institutions: Uppsala University, University of Copenhagen, Harvard University, Massachusetts Institute of Technology

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2984673553

FWCI: 1.002

Cites: 49

Cited by: 16

Related to: 10