English

Higher-order Comparisons of Sentence Encoder Representations

Computation and Language 2019-09-06 v2

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

Keywords

Cite

@article{arxiv.1909.00303,
  title  = {Higher-order Comparisons of Sentence Encoder Representations},
  author = {Mostafa Abdou and Artur Kulmizev and Felix Hill and Daniel M. Low and Anders Søgaard},
  journal= {arXiv preprint arXiv:1909.00303},
  year   = {2019}
}

Comments

EMNLP 2019

R2 v1 2026-06-23T11:02:18.860Z