Alessandro Roncone


pdf bib
Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next
Katharina Kann | Abteen Ebrahimi | Joewie Koh | Shiran Dudy | Alessandro Roncone
Proceedings of the 4th Workshop on NLP for Conversational AI

Human–computer conversation has long been an interest of artificial intelligence and natural language processing research. Recent years have seen a dramatic improvement in quality for both task-oriented and open-domain dialogue systems, and an increasing amount of research in the area. The goal of this work is threefold: (1) to provide an overview of recent advances in the field of open-domain dialogue, (2) to summarize issues related to ethics, bias, and fairness that the field has identified as well as typical errors of dialogue systems, and (3) to outline important future challenges. We hope that this work will be of interest to both new and experienced researchers in the area.


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.