Le traitement du langage naturel à l'ère de l'IA générative
Rejoignez-nous à Mila en octobre pour un atelier de trois jour visant à explorer le potentiel de transformation des technologies langagières et leurs implications pour la société.
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
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
We develop a stochastic differential equation, called homogenized SGD, for analyzing the dynamics of stochastic gradient descent (SGD) on a … (voir plus)high-dimensional random least squares problem with
Robot operating in an open world can encounter
novel objects with unknown physical properties, such as mass,
friction, or size. It is desira… (voir plus)ble to be able to sense those
property through contact-rich interaction, before performing
downstream tasks with the objects. We propose a method for
autonomously learning active tactile perception policies, by
learning a generative world model leveraging a differentiable
bayesian filtering algorithm, and designing an information-
gathering model predictive controller. We test the method on
three simulated tasks: mass estimation, height estimation and
toppling height estimation. Our method is able to discover
policies which gather information about the desired property
in an intuitive manner.
Abstract Sequences derived from the Long INterspersed Element-1 (L1) family of retrotransposons occupy at least 17% of the human genome, wit… (voir plus)h 67 distinct subfamilies representing successive waves of expansion and extinction in mammalian lineages. L1s contribute extensively to gene regulation, but their molecular history is difficult to trace, because most are present only as truncated and highly mutated fossils. Consequently, L1 entries in current databases of repeat sequences are composed mainly of short diagnostic subsequences, rather than full functional progenitor sequences for each subfamily. Here, we have coupled 2 levels of sequence reconstruction (at the level of whole genomes and L1 subfamilies) to reconstruct progenitor sequences for all human L1 subfamilies that are more functionally and phylogenetically plausible than existing models. Most of the reconstructed sequences are at or near the canonical length of L1s and encode uninterrupted ORFs with expected protein domains. We also show that the presence or absence of binding sites for KRAB-C2H2 Zinc Finger Proteins, even in ancient-reconstructed progenitor L1s, mirrors binding observed in human ChIP-exo experiments, thus extending the arms race and domestication model. RepeatMasker searches of the modern human genome suggest that the new models may be able to assign subfamily resolution identities to previously ambiguous L1 instances. The reconstructed L1 sequences will be useful for genome annotation and functional study of both L1 evolution and L1 contributions to host regulatory networks.
In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationa… (voir plus)ry. This assumption of stationarity, while simplifying, can be unrealistic in many scenarios. In the continual reinforcement learning scenario, the sequence of tasks is another source of nonstationarity. In this work, we propose to examine this continual reinforcement learning setting through the Block Contextual MDP (BC-MDP) framework, which enables us to relax the assumption of stationarity. This framework challenges RL algorithms to handle both nonstationarity and rich observation settings and, by additionally leveraging smoothness properties, enables us to study generalization bounds for this setting. Finally, we take inspiration from adaptive control to propose a novel algorithm that addresses the challenges introduced by this more realistic BC-MDP setting, allows for zero-shot adaptation at evaluation time, and achieves strong performance on several nonstationary environments.
2022-05-11
Proceedings of The 4th Annual Learning for Dynamics and Control Conference (publié)
Interpreting the predictions of existing Question Answering (QA) models is critical to many real-world intelligent applications, such as QA … (voir plus)systems for healthcare, education, and finance. However, existing QA models lack interpretability and provide no feedback or explanation for end-users to help them understand why a specific prediction is the answer to a question. In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models. Unlike previous research that simply extracts several sentence(s) in the context as evidence, we are the first to explicitly define the concept of evidence as the supporting facts in a context which are informative, concise, and readable. Besides, we provide effective strategies to quantitatively measure the informativeness, conciseness and readability of evidence. Furthermore, we propose Grow-and-Clip Evidence Distillation (GCED) algorithm to extract evidences from the contexts by trade-off informativeness, conciseness, and readability. We conduct extensive experiments on the SQuAD and TriviaQA datasets with several baseline models to evaluate the effect of GCED on interpreting answers to questions. Human evaluation are also carried out to check the quality of distilled evidences. Experimental results show that automatic distilled evidences have human-like informativeness, conciseness and readability, which can enhance the interpretability of the answers to questions.
2022-05-09
2022 IEEE 38th International Conference on Data Engineering (ICDE) (publié)
Meaningful performance assessment of biomedical image analysis algorithms depends on objective and appropriate performance metrics. There ar… (voir plus)e major shortcomings in the current state of the art. Yet, so far limited attention has been paid to practical pitfalls associated when using particular metrics for image analysis tasks. Therefore, a number of international initiatives have collaborated to offer researchers with guidance and tools for selecting performance metrics in a problem-aware manner. In our proposed framework, the characteristics of the given biomedical problem are first captured in a problem fingerprint, which identifies properties related to domain interests, the target structure(s), the input datasets, and algorithm output. A problem category-specific mapping is applied in the second step to match fingerprints to metrics that reflect domain requirements. Based on input from experts from more than 60 institutions worldwide, we believe our metric recommendation framework to be useful to the MIDL community and to enhance the quality of biomedical image analysis algorithm validation.
Recent years have witnessed the dramatic growth of paper volumes with plenty of new research papers published every day, especially in the a… (voir plus)rea of computer science. How to glean papers worth reading from the massive literature to do a quick survey or keep up with the latest advancement about a specific research topic has become a challenging task. Existing academic search engines return relevant papers by individually calculating the relevance between each paper and query. However, such systems usually omit the prerequisite chains of a research topic and cannot form a meaningful reading path. In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query. To serve as a research benchmark, we further propose SurveyBank, a dataset consisting of large quantities of survey papers in the field of computer science as well as their citation relationships. Furthermore, we propose a graph-optimization-based approach for reading path generation which takes the relationship between papers into account. Extensive evaluations demonstrate that our approach outperforms other baselines. A real-time Reading Path Generation (RePaGer) system has been also implemented with our designed model. Our source code and SurveyBank dataset can be found here11https://github.com/JiayuanDing100/Reading-Path-Generation.
2022-05-09
2022 IEEE 38th International Conference on Data Engineering (ICDE) (publié)