Publications

Methods, Applications, and Directions of Learning-to-Rank in NLP Research
Justin Lee
Gabriel Bernier-Colborne
Tegan Maharaj
Sowmya Vajjala
Learning-to-rank (LTR) algorithms aim to order a set of items according to some criteria. They are at the core of applications such as web s… (see more)earch and social media recommendations, and are an area of rapidly increasing interest, with the rise of large language models (LLMs) and the widespread impact of these technologies on society. In this paper, we survey the diverse use cases of LTR methods in natural language processing (NLP) research, looking at previously under-studied aspects such as multilingualism in LTR applications and statistical significance testing for LTR problems. We also consider how large language models are changing the LTR landscape. This survey is aimed at NLP researchers and practitioners interested in understanding the formalisms and best practices regarding the application of LTR approaches in their research.
2024-05-31
Findings of the Association for Computational Linguistics: NAACL 2024 (published)
doi.org
"One-Size-Fits-All"? Examining Expectations around What Constitute"Fair"or"Good"NLG System Behaviors
Li Lucy
Su Lin Blodgett
Milad Shokouhi
Hanna Wallach
A.R. Olteanu
Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to beh… (see more)ave identically for social groups, to adaptation, where behaviors should instead vary across them. To illuminate tensions around invariance and adaptation, we conduct five case studies, in which we perturb different types of identity-related language features (names, roles, locations, dialect, and style) in NLG system inputs. Through these cases studies, we examine people's expectations of system behaviors, and surface potential caveats of these contrasting yet commonly held assumptions. We find that motivations for adaptation include social norms, cultural differences, feature-specific information, and accommodation; in contrast, motivations for invariance include perspectives that favor prescriptivism, view adaptation as unnecessary or too difficult for NLG systems to do appropriately, and are wary of false assumptions. Our findings highlight open challenges around what constitute"fair"or"good"NLG system behaviors.
2024-05-31
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (published)
doi.org
arxiv.org
PCR191 Patient-Centric Assessment of Treatment Experience in Breast Cancer: Development and Validation of a Patient Questionnaire
K. Gurjar
B. Rattanavong
L. Bennetts
J. Sahota
M. Ouerghi
C. Ammendolea
J. Asselah
S. Bartlett
C. Brezden-Masley
J. Croke
T. Hijal
J. Kildea
J. Papadakos
L. Watson
D. Soliman
2024-05-31
Value in Health (published)
doi.org
Pioneering women in nuclear and radiation sciences
Mirta Dumancic
S. Enger
2024-05-31
Radiotherapy and Oncology (published)
doi.org
Protocol to perform integrative analysis of high-dimensional single-cell multimodal data using an interpretable deep learning technique
Manqi Zhou
Hao Zhang
Zilong Bai
Dylan Mann-Krzisnik
Fei Wang
Yue Li
2024-05-31
STAR Protocols (published)
doi.org
Reducing Two-Way Ranging Variance by Signal-Timing Optimization
Mohammed Ayman Shalaby
Charles Champagne Cossette
James Richard Forbes
Jerome Le Ny
Time-of-flight-based ranging among transceivers with different clocks requires protocols that accommodate varying rates of the clocks. Doubl… (see more)e-sided two-way ranging (DS-TWR) is widely adopted as a standard protocol due to its accuracy; however, the precision of DS-TWR has not been clearly addressed. In this paper, an analytical model of the variance of DS-TWR is derived as a function of the user-programmed response delays, which is then compared to the Cramer-Rao Lower Bound (CRLB). This is then used to formulate an optimization problem over the response delays in order to maximize the information gained from range measurements. The derived analytical variance model and optimized protocol are validated experimentally with 2 ranging UWB transceivers, where 29 million range measurements are collected.
2024-05-31
IEEE Transactions on Aerospace and Electronic Systems (published)
doi.org
arxiv.org
A responsible framework for applying artificial intelligence on medical images and signals at the point-of-care: the PACS-AI platform.
Pascal Theriault-Lauzier
Denis Cobin
Olivier Tastet
Élodie Labrecque Langlais
B. Taji
Guson Kang
A. Chong
Derek So
An Tang
Judy Wawira Gichoya
A. Chandar
Pierre-Luc Deziel
Julie G Hussin
Samuel Kadoury
Robert Avram
2024-05-31
Canadian Journal of Cardiology (published)
doi.org
Revisiting the 2023 wildfire season in Canada
Flavie Pelletier
Jeffrey A. Cardille
Michael A. Wulder
Joanne C. White
Txomin Hermosilla
2024-05-31
Science of Remote Sensing (published)
doi.org
Stimulus information guides the emergence of behavior-related signals in primary somatosensory cortex during learning
Mariangela Panniello
Colleen J. Gillon
Roberto Maffulli
Marco Celotto
Blake A. Richards
Stefano Panzeri
Michael M. Kohl
Neurons in the primary cortex carry sensory- and behavior-related information, but it remains an open question how this information emerges … (see more)and intersects together during learning. Current evidence points to two possible learning-related changes: sensory information increases in the primary cortex or sensory information remains stable, but its readout efficiency in association cortices increases. We investigated this question by imaging neuronal activity in mouse primary somatosensory cortex before, during, and after learning of an object localization task. We quantified sensory- and behavior-related information and estimated how much sensory information was used to instruct perceptual choices as learning progressed. We find that sensory information increases from the start of training, while choice information is mostly present in the later stages of learning. Additionally, the readout of sensory information becomes more efficient with learning as early as in the primary sensory cortex. Together, our results highlight the importance of primary cortical neurons in perceptual learning.
2024-05-31
Cell Reports (published)
doi.org
Climate Variable Downscaling with Conditional Normalizing Flows
Christina Winkler
Paula Harder
David Rolnick
Predictions of global climate models typically operate on coarse spatial scales due to the large computational costs of climate simulations.… (see more) This has led to a considerable interest in methods for statistical downscaling, a similar process to super-resolution in the computer vision context, to provide more local and regional climate information. In this work, we apply conditional normalizing flows to the task of climate variable downscaling. We showcase its successful performance on an ERA5 water content dataset for different upsampling factors. Additionally, we show that the method allows us to assess the predictive uncertainty in terms of standard deviation from the fitted conditional distribution mean.
2024-05-30
ArXiv (preprint)
doi.org
arxiv.org
How well do models of visual cortex generalize to out of distribution samples?
Yifei Ren
Pouya Bashivan
2024-05-30
PLOS Computational Biology (published)
doi.org
Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide
Alexis Nolin-Lapalme
Pascal Theriault-Lauzier
Denis Corbin
Olivier Tastet
Abhinav Sharma
Julie G. Hussin
Samuel Kadoury
River Jiang
Andrew D. Krahn
Richard Gallo
Robert Avram
Large language models (LLMs) have emerged as powerful tools in artificial intelligence, demonstrating remarkable capabilities in natural lan… (see more)guage processing and generation. In this article, we explore the potential applications of LLMs in enhancing cardiovascular care and research. We discuss how LLMs can be utilized to simplify complex medical information, improve patient-physician communication, and automate tasks such as summarizing medical articles and extracting key information. Additionally, we highlight the role of LLMs in categorizing and analyzing unstructured data, such as medical notes and test results, which could revolutionize data handling and interpretation in cardiovascular research. However, we also emphasize the limitations and challenges associated with LLMs, including potential biases, reasoning opacity, and the need for rigorous validation in medical contexts. This article provides a practical guide for cardiovascular professionals to understand and harness the power of LLMs while navigating their limitations. We conclude by discussing the future directions and implications of LLMs in transforming cardiovascular care and research. Large language models (LLMs) have emerged as powerful tools in artificial intelligence, demonstrating remarkable capabilities in natural language processing and generation. In this article, we explore the potential applications of LLMs in enhancing cardiovascular care and research. We discuss how LLMs can be utilized to simplify complex medical information, improve patient-physician communication, and automate tasks such as summarizing medical articles and extracting key information. Additionally, we highlight the role of LLMs in categorizing and analyzing unstructured data, such as medical notes and test results, which could revolutionize data handling and interpretation in cardiovascular research. However, we also emphasize the limitations and challenges associated with LLMs, including potential biases, reasoning opacity, and the need for rigorous validation in medical contexts. This article provides a practical guide for cardiovascular professionals to understand and harness the power of LLMs while navigating their limitations. We conclude by discussing the future directions and implications of LLMs in transforming cardiovascular care and research. Les modèles de langage à grande échelle (LLM) sont devenus des outils puissants en intelligence artificielle, démontrant des capacités remarquables dans le traitement et la génération du langage naturel. Dans cet article, nous explorons les applications potentielles des LLM pour améliorer les soins et la recherche cardiovasculaires. Nous discutons de la manière dont les LLM peuvent être utilisés pour simplifier des informations médicales complexes, améliorer la communication patient-médecin et automatiser des tâches telles que la synthèse d'articles médicaux et l'extraction d'informations clés. De plus, nous soulignons le rôle des LLM dans la catégorisation et l'analyse des données non structurées, telles que les notes médicales et les résultats des tests, ce qui pourrait révolutionner la gestion et l'interprétation des données dans la recherche cardiovasculaire. Cependant, nous soulignons également les limites et les défis associés aux LLM, notamment les biais potentiels, l'opacité de leur raisonnement et la nécessité d'une validation rigoureuse dans les contextes médicaux. Cet article fournit un guide pratique aux professionnels cardiovasculaires pour comprendre et exploiter la puissance des LLM tout en naviguant dans leurs limites. Nous concluons en discutant des orientations futures et des implications des LLM dans la transformation des soins et de la recherche cardiovasculaires. Les modèles de langage à grande échelle (LLM) sont devenus des outils puissants en intelligence artificielle, démontrant des capacités remarquables dans le traitement et la génération du langage naturel. Dans cet article, nous explorons les applications potentielles des LLM pour améliorer les soins et la recherche cardiovasculaires. Nous discutons de la manière dont les LLM peuvent être utilisés pour simplifier des informations médicales complexes, améliorer la communication patient-médecin et automatiser des tâches telles que la synthèse d'articles médicaux et l'extraction d'informations clés. De plus, nous soulignons le rôle des LLM dans la catégorisation et l'analyse des données non structurées, telles que les notes médicales et les résultats des tests, ce qui pourrait révolutionner la gestion et l'interprétation des données dans la recherche cardiovasculaire. Cependant, nous soulignons également les limites et les défis associés aux LLM, notamment les biais potentiels, l'opacité de leur raisonnement et la nécessité d'une validation rigoureuse dans les contextes médicaux. Cet article fournit un guide pratique aux professionnels cardiovasculaires pour comprendre et exploiter la puissance des LLM tout en naviguant dans leurs limites. Nous concluons en discutant des orientations futures et des implications des LLM dans la transformation des soins et de la recherche cardiovasculaires.
2024-05-30
Canadian Journal of Cardiology (published)
doi.org