/RD-UU-MPLT

Mitigating a language model's over-confidence with NLI predictions on Multi-NLI hypotheses with random word order using PAWS (paraphrase) and Winogrande (anaphora).

Primary LanguageJupyter Notebook

Additional Paraphrase Training Drives Language Models Closer to Human Behaviour on Natural Language Inference

A Research and Development project.

Refer to the Jupyter notebook for now.