Johannes Mario Meissner — accepted AI-conference papers

2022

Debiasing Masks: A New Framework for Shortcut Mitigation in NLU

Johannes Mario Meissner, Saku Sugawara, Akiko Aizawa

EMNLP 2022main

Debiasing language models from unwanted behaviors in Natural Language Understanding (NLU) tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and avoid uncovering more advanced and desirable linguisti…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2021

Embracing Ambiguity: Shifting the Training Target of NLI Models

Johannes Mario Meissner, Napat Thumwanit, Saku Sugawara, Akiko Aizawa

ACL 2021short

Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels. While many research works do not pay much attention to this fact, several recent efforts have been made to acknowledge and embrace the existence of ambiguity, such as UNLI and ChaosNLI. In this paper, we explore…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗