Higher-order Comparisons of Sentence Encoder Representations

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Higher-order Comparisons of Sentence Encoder Representations. / vqc439, vqc439; Kulmizev, Artur ; Hill, Felix ; Low, Daniel M. Low; Søgaard, Anders.

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 2019. p. 5838–5845.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

vqc439, V, Kulmizev, A, Hill, F, Low, DML & Søgaard, A 2019, Higher-order Comparisons of Sentence Encoder Representations. in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, pp. 5838–5845, 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 03/11/2019.

APA

vqc439, V., Kulmizev, A., Hill, F., Low, D. M. L., & Søgaard, A. (2019). Higher-order Comparisons of Sentence Encoder Representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (pp. 5838–5845). Association for Computational Linguistics.

Vancouver

vqc439 V, Kulmizev A, Hill F, Low DML, Søgaard A. Higher-order Comparisons of Sentence Encoder Representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics. 2019. p. 5838–5845

Author

vqc439, vqc439 ; Kulmizev, Artur ; Hill, Felix ; Low, Daniel M. Low ; Søgaard, Anders. / Higher-order Comparisons of Sentence Encoder Representations. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 2019. pp. 5838–5845

Bibtex

@inproceedings{a83067d8f4c94354afa2e103ad8314cb,
title = "Higher-order Comparisons of Sentence Encoder Representations",
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.",
author = "vqc439 vqc439 and Artur Kulmizev and Felix Hill and Low, {Daniel M. Low} and Anders S{\o}gaard",
year = "2019",
language = "English",
pages = "5838–5845",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing",
publisher = "Association for Computational Linguistics",
note = "2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) ; Conference date: 03-11-2019 Through 07-11-2019",

}

RIS

TY - GEN

T1 - Higher-order Comparisons of Sentence Encoder Representations

AU - vqc439, vqc439

AU - Kulmizev, Artur

AU - Hill, Felix

AU - Low, Daniel M. Low

AU - Søgaard, Anders

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

M3 - Article in proceedings

SP - 5838

EP - 5845

BT - Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing

PB - Association for Computational Linguistics

T2 - 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Y2 - 3 November 2019 through 7 November 2019

ER -

ID: 240321267