Stéphane Aroca-Ouellette


pdf bib
PROST: Physical Reasoning about Objects through Space and Time
Stéphane Aroca-Ouellette | Cory Paik | Alessandro Roncone | Katharina Kann
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color
Cory Paik | Stéphane Aroca-Ouellette | Alessandro Roncone | Katharina Kann
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent work has raised concerns about the inherent limitations of text-only pretraining. In this paper, we first demonstrate that reporting bias, the tendency of people to not state the obvious, is one of the causes of this limitation, and then investigate to what extent multimodal training can mitigate this issue. To accomplish this, we 1) generate the Color Dataset (CoDa), a dataset of human-perceived color distributions for 521 common objects; 2) use CoDa to analyze and compare the color distribution found in text, the distribution captured by language models, and a human’s perception of color; and 3) investigate the performance differences between text-only and multimodal models on CoDa. Our results show that the distribution of colors that a language model recovers correlates more strongly with the inaccurate distribution found in text than with the ground-truth, supporting the claim that reporting bias negatively impacts and inherently limits text-only training. We then demonstrate that multimodal models can leverage their visual training to mitigate these effects, providing a promising avenue for future research.


pdf bib
On Losses for Modern Language Models
Stéphane Aroca-Ouellette | Frank Rudzicz
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

BERT set many state-of-the-art results over varied NLU benchmarks by pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP), the latter of which has been highly criticized. In this paper, we 1) clarify NSP’s effect on BERT pre-training, 2) explore fourteen possible auxiliary pre-training tasks, of which seven are novel to modern language models, and 3) investigate different ways to include multiple tasks into pre-training. We show that NSP is detrimental to training due to its context splitting and shallow semantic signal. We also identify six auxiliary pre-training tasks – sentence ordering, adjacent sentence prediction, TF prediction, TF-IDF prediction, a FastSent variant, and a Quick Thoughts variant – that outperform a pure MLM baseline. Finally, we demonstrate that using multiple tasks in a multi-task pre-training framework provides better results than using any single auxiliary task. Using these methods, we outperform BERTBase on the GLUE benchmark using fewer than a quarter of the training tokens.