Higher-order Comparisons of Sentence Encoder Representations
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- OA.Higher-order Comparisons of Sentence Encoder Representations
Forlagets udgivne version, 1,12 MB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2019 |
Sider | 5838–5845 |
Status | Udgivet - 2019 |
Begivenhed | 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) - Hong Kong, Kina Varighed: 3 nov. 2019 → 7 nov. 2019 |
Konference
Konference | 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
---|---|
Land | Kina |
By | Hong Kong |
Periode | 03/11/2019 → 07/11/2019 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 240321267