Dans un nouvel article, David Rolnick et ses collègues affirment que la recherche en IA axée sur les problèmes contribuera à accroître l'efficacité à long terme de l'IA.
Ce programme est conçu pour fournir aux professionnel·le·s travaillant dans le domaine de la politique une compréhension fondamentale de la technologie de l'IA.
Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
StereoSet: Measuring stereotypical bias in pretrained language models
A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or African Americans are athlet… (voir plus)ic. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real-world data, they are known to capture stereotypical biases. It is important to quantify to what extent these biases are present in them. Although this is a rapidly growing area of research, existing literature lacks in two important aspects: 1) they mainly evaluate bias of pretrained language models on a small set of artificial sentences, even though these models are trained on natural data 2) current evaluations focus on measuring bias without considering the language modeling ability of a model, which could lead to misleading trust on a model even if it is a poor language model. We address both these problems. We present StereoSet, a large-scale natural English dataset to measure stereotypical biases in four domains: gender, profession, race, and religion. We contrast both stereotypical bias and language modeling ability of popular models like BERT, GPT-2, RoBERTa, and XLnet. We show that these models exhibit strong stereotypical biases. Our data and code are available at https://stereoset.mit.edu.
2021-08-01
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)
Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision … (voir plus)medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. Materials and Methods: We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a closed-form collapsed variational inference algorithm to learn the model distributions of MixEHR-S. Results: We applied MixEHR-S to two independent large-scale EHR databases in Quebec with three targeted applications: (1) Congenital Heart Disease (CHD) diagnostic prediction among 154,775 patients; (2) Chronic obstructive pulmonary disease (COPD) diagnostic prediction among 73,791 patients; (3) future insulin treatment prediction among 78,712 patients diagnosed with diabetes as a mean to assess the disease exacerbation. In all three applications, MixEHR-S conferred clinically meaningful latent topics among the most predictive latent topics and achieved superior target prediction accuracy compared to the existing methods, providing opportunities for prioritizing high-risk patients for healthcare services. Availability and implementation: MixEHR-S source code and scripts of the experiments are freely available at https://github.com/li-lab-mcgill/mixehrS
2021-08-01
Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (publié)
Recent studies report that socioeconomic status (SES) correlates with brain structure. Yet, such findings are variable and little is known a… (voir plus)bout underlying causes. We present a well-powered voxel-based analysis of grey matter volume (GMV) across levels of SES, finding many small SES effects widely distributed across the brain, including cortical, subcortical and cerebellar regions. We also construct a polygenic index of SES to control for the additive effects of common genetic variation related to SES, which attenuates observed SES-GMV relations, to different degrees in different areas. Remaining variance, which may be attributable to environmental factors, is substantially accounted for by body mass index, a marker for lifestyle related to SES. In sum, SES affects multiple brain regions through measurable genetic and environmental effects. One-sentence Summary Socioeconomic status is linked with brain anatomy through a varying balance of genetic and environmental influences.
Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models … (voir plus)are surprisingly insensitive to the order of words.In this paper, we investigate this phenomenon by developing order-altering perturbations on the order of words, subwords, and characters to analyze their effect on neural models’ performance on language understanding tasks.We experiment with measuring the impact of perturbations to the local neighborhood of characters and global position of characters in the perturbed texts and observe that perturbation functions found in prior literature only affect the global ordering while the local ordering remains relatively unperturbed.We empirically show that neural models, invariant of their inductive biases, pretraining scheme, or the choice of tokenization, mostly rely on the local structure of text to build understanding and make limited use of the global structure.
Background: There is a growing recognition that strategies to reduce SARS-CoV-2 transmission should be responsive to local transmission dyna… (voir plus)mics. Studies have revealed inequalities along social determinants of health, but little investigation was conducted surrounding geographic concentration within cities. We quantified social determinants of geographic concentration of COVID-19 cases across sixteen census metropolitan areas (CMA) in four Canadian provinces. Methods: We used surveillance data on confirmed COVID-19 cases at the level of dissemination area. Gini (co-Gini) coefficients were calculated by CMA based on the proportion of the population in ranks of diagnosed cases and each social determinant using census data (income, education, visible minority, recent immigration, suitable housing, and essential workers) and the corresponding share of cases. Heterogeneity was visualized using Lorenz (concentration) curves. Results: Geographic concentration was observed in all CMAs (half of the cumulative cases were concentrated among 21-35% of each city's population): with the greatest geographic heterogeneity in Ontario CMAs (Gini coefficients, 0.32-0.47), followed by British Columbia (0.23-0.36), Manitoba (0.32), and Quebec (0.28-0.37). Cases were disproportionately concentrated in areas with lower income, education attainment, and suitable housing; and higher proportion of visible minorities, recent immigrants, and essential workers. Although a consistent feature across CMAs was concentration by proportion visible minorities, the magnitude of concentration by social determinants varied across CMAs. Interpretation: The feature of geographical concentration of COVID-19 cases was consistent across CMAs, but the pattern by social determinants varied. Geographically-prioritized allocation of resources and services should be tailored to the local drivers of inequalities in transmission in response to SARS-CoV-2's resurgence.