The Self-Contained Negation Test Set

David Kletz, Pascal Amsili, Marie Candito


Abstract
Several methodologies have recently been proposed to evaluate the ability of Pretrained Language Models (PLMs) to interpret negation. In this article, we build on Gubelmann and Handschuh (2022), which studies the modification of PLMs’ predictions as a function of the polarity of inputs, in English. Crucially, this test uses “self-contained” inputs ending with a masked position: depending on the polarity of a verb in the input, a particular token is either semantically ruled out or allowed at the masked position. By replicating Gubelmann and Handschuh (2022) experiments, we have uncovered flaws that weaken the conclusions that can be drawn from this test. We thus propose an improved version, the Self-Contained Neg Test, which is more controlled, more systematic, and entirely based on examples forming minimal pairs varying only in the presence or absence of verbal negation in English. When applying our test to the roberta and bert base and large models, we show that only roberta-large shows trends that match the expectations, while bert-base is mostly insensitive to negation. For all the tested models though, in a significant number of test instances the top-1 prediction remains the token that is semantically forbidden by the context, which shows how much room for improvement remains for a proper treatment of the negation phenomenon.
Anthology ID:
2023.blackboxnlp-1.16
Volume:
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2023
Address:
Singapore
Editors:
Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi
Venues:
BlackboxNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
212–221
Language:
URL:
https://aclanthology.org/2023.blackboxnlp-1.16
DOI:
10.18653/v1/2023.blackboxnlp-1.16
Bibkey:
Cite (ACL):
David Kletz, Pascal Amsili, and Marie Candito. 2023. The Self-Contained Negation Test Set. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 212–221, Singapore. Association for Computational Linguistics.
Cite (Informal):
The Self-Contained Negation Test Set (Kletz et al., BlackboxNLP-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.blackboxnlp-1.16.pdf