Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation

Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina, Viktoria Knyazkova, Tatiana Shavrina


Abstract
Linguistic analysis of language models is one of the ways to explain and describe their reasoning, weaknesses, and limitations. In the probing part of the model interpretability research, studies concern individual languages as well as individual linguistic structures. The question arises: are the detected regularities linguistically coherent, or on the contrary, do they dissonate at the typological scale? Moreover, the majority of studies address the inherent set of languages and linguistic structures, leaving the actual typological diversity knowledge out of scope. In this paper, we present and apply the GUI-assisted framework allowing us to easily probe massive amounts of languages for all the morphosyntactic features present in the Universal Dependencies data. We show that reflecting the anglo-centric trend in NLP over the past years, most of the regularities revealed in the mBERT model are typical for the western-European languages. Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards, allowing practitioners to use and share their familiar probing methods to interpret multilingual models. Thus we propose a toolkit to systematize the multilingual flaws in multilingual models, providing a reproducible experimental setup for 104 languages and 80 morphosyntactic features.
Anthology ID:
2022.blackboxnlp-1.37
Volume:
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
441–456
Language:
URL:
https://aclanthology.org/2022.blackboxnlp-1.37
DOI:
10.18653/v1/2022.blackboxnlp-1.37
Bibkey:
Cite (ACL):
Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina, Viktoria Knyazkova, and Tatiana Shavrina. 2022. Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 441–456, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation (Serikov et al., BlackboxNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.blackboxnlp-1.37.pdf