Higher-order Comparisons of Sentence Encoder Representations

Autor:	Abdou, Mostafa, Kulmizev, Artur, Hill, Felix, Low, Daniel M., Søgaard, Anders
Rok vydání:	2019
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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 Comment: EMNLP 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1909.00303 Zobrazit plný text záznamu View this record from Arxiv