A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs

Mareike Hartmann, Miryam de Lhoneux, Daniel Hershcovich, Yova Kementchedjhieva, Lukas Nielsen, Chen Qiu, Anders Søgaard


Abstract
Negation is one of the most fundamental concepts in human cognition and language, and several natural language inference (NLI) probes have been designed to investigate pretrained language models’ ability to detect and reason with negation. However, the existing probing datasets are limited to English only, and do not enable controlled probing of performance in the absence or presence of negation. In response, we present a multilingual (English, Bulgarian, German, French and Chinese) benchmark collection of NLI examples that are grammatical and correctly labeled, as a result of manual inspection and reformulation. We use the benchmark to probe the negation-awareness of multilingual language models and find that models that correctly predict examples with negation cues, often fail to correctly predict their counter-examples without negation cues, even when the cues are irrelevant for semantic inference.
Anthology ID:
2021.conll-1.19
Volume:
Proceedings of the 25th Conference on Computational Natural Language Learning
Month:
November
Year:
2021
Address:
Online
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
244–257
Language:
URL:
https://aclanthology.org/2021.conll-1.19
DOI:
10.18653/v1/2021.conll-1.19
Bibkey:
Cite (ACL):
Mareike Hartmann, Miryam de Lhoneux, Daniel Hershcovich, Yova Kementchedjhieva, Lukas Nielsen, Chen Qiu, and Anders Søgaard. 2021. A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 244–257, Online. Association for Computational Linguistics.
Cite (Informal):
A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs (Hartmann et al., CoNLL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.conll-1.19.pdf
Video:
 https://aclanthology.org/2021.conll-1.19.mp4
Code
 mahartmann/negationminpairs
Data
MultiNLISNLI