Joe Stacey

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 11

Top Topics

Automatically Generated

Multiple Domains

Natural Language

Logical Reasoning

Top Venues

Publications

Joe Stacey, Marek Rei
Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation. ACL (Findings) (2024)
Joe Stacey, Jianpeng Cheng, John Torr, Tristan Guigue, Joris Driesen, Alexandru Coca, Mark Gaynor, Anders Johannsen
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues. CoRR (2024)
Abhilasha Ravichander, Joe Stacey, Marek Rei
When and Why Does Bias Mitigation Work? EMNLP (Findings) (2023)
Joe Stacey, Marek Rei
Improving Robustness in Knowledge Distillation Using Domain-Targeted Data Augmentation. CoRR (2023)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Oana-Maria Camburu, Marek Rei
Logical Reasoning for Natural Language Inference Using Generated Facts as Atoms. CoRR (2023)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Marek Rei
Logical Reasoning with Span Predictions: Span-level Logical Atoms for Interpretable and Robust NLI Models. CoRR (2022)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Marek Rei
Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models. EMNLP (2022)
Joe Stacey, Yonatan Belinkov, Marek Rei
Supervising Model Attention with Human Explanations for Robust Natural Language Inference. AAAI (2022)
Joe Stacey, Yonatan Belinkov, Marek Rei
Natural Language Inference with a Human Touch: Using Human Explanations to Guide Model Attention. CoRR (2021)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Sebastian Riedel, Tim Rocktäschel
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training. EMNLP (1) (2020)
Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Sebastian Riedel, Tim Rocktäschel
There is Strength in Numbers: Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training. CoRR (2020)