Naturalistic Causal Probing for Morpho-Syntax
Transactions of the Association for Computational Linguistics · 09.05.2023 · 11 · 384-403
DOI: 10.1162/tacl_a_00554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 09.05.2023. Verfasst von Afra Amini und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing. However, there is still a lack of understanding of the limitations and weaknesses of various types of probes. In this work, we suggest a strategy for input-level intervention on naturalistic sentences. Using our approach, we intervene on the morpho-syntactic features of a sentence, while keeping the rest of the sentence unchanged. Such an intervention allows us to causally probe pre-trained models. We apply our naturalistic causal probing framework to analyze the effects of grammatical gender and number on contextualized representations extracted from three pre-trained models in Spanish, the multilingual versions of BERT, RoBERTa, and GPT-2. Our experiments suggest that naturalistic interventions lead to stable estimates of the causal effects of various linguistic properties. Moreover, our experiments demonstrate the importance of naturalistic causal probing when analyzing pre-trained models. https://github.com/rycolab/naturalistic-causal-probing
Zitieren
APA
Amini, A., Pimentel, T., Meister, C., & Cotterell, R. (2023). Naturalistic Causal Probing for Morpho-Syntax. Transactions of the Association for Computational Linguistics, 11, 384-403. https://doi.org/10.1162/tacl_a_00554
Vancouver
Amini A, Pimentel T, Meister C, Cotterell R. Naturalistic Causal Probing for Morpho-Syntax. Transactions of the Association for Computational Linguistics. 2023;11:384-403. doi:10.1162/tacl_a_00554
BibTeX
@article{Amini2023,
author = {Amini, Afra and Pimentel, Tiago and Meister, Clara and Cotterell, Ryan},
title = {Naturalistic Causal Probing for Morpho-Syntax},
journal = {Transactions of the Association for Computational Linguistics},
year = {2023},
volume = {11},
pages = {384--403},
doi = {10.1162/tacl_a_00554}
}
EUVIMED