Performance Prediction via Bayesian Matrix Factorisation for Multilingual Natural Language Processing Tasks

Viktoria Schram, Daniel Beck, Trevor Cohn


Abstract
Performance prediction for Natural Language Processing (NLP) seeks to reduce the experimental burden resulting from the myriad of different evaluation scenarios, e.g., the combination of languages used in multilingual transfer. In this work, we explore the framework ofBayesian matrix factorisation for performance prediction, as many experimental settings in NLP can be naturally represented in matrix format. Our approach outperforms the state-of-the-art in several NLP benchmarks, including machine translation and cross-lingual entity linking. Furthermore, it also avoids hyperparameter tuning and is able to provide uncertainty estimates over predictions.
Anthology ID:
2023.eacl-main.131
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1790–1801
Language:
URL:
https://aclanthology.org/2023.eacl-main.131
DOI:
10.18653/v1/2023.eacl-main.131
Bibkey:
Cite (ACL):
Viktoria Schram, Daniel Beck, and Trevor Cohn. 2023. Performance Prediction via Bayesian Matrix Factorisation for Multilingual Natural Language Processing Tasks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1790–1801, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Performance Prediction via Bayesian Matrix Factorisation for Multilingual Natural Language Processing Tasks (Schram et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.131.pdf
Video:
 https://aclanthology.org/2023.eacl-main.131.mp4