Bonjour,
Mail de rappel pour indiquer vos préférences pour la date du prochain séminaire de
l'axe :
https://framadate.org/wWW99oIRX3syHien
Pour rappel il sera donné par Behrooz Omidvar-Tehrani (
http://omidvar.info/), chercheur à
Amazon AI labs en Californie, (cf. Le premier mail pour plus d'infos sur le talk)
Je fixe la date du séminaire demain (Mercredi 11)
Bien à vous,
Idir
[Une image contenant texte, clipart, signe Description générée automatiquement]
Idir Benouaret
Enseignant-Chercheur
[
https://lh6.googleusercontent.com/dCYVl9pmYNgg1wBndkYtELRR9DX8RRY5d_e4N2Xhk…]
[
https://lh4.googleusercontent.com/O8lm18dZZ188g_iBNOmO2UX8qPx8zNmCfFbItUDzk…]
[
https://lh4.googleusercontent.com/iJejRKKnVTGA2lyz-eMOKQvI9vVP-ftzUIqzCoeoR…]
[
https://lh6.googleusercontent.com/J3eMugeLIjhhZigE4aw44kR3o5SCCOf3J7YJfPDTC…]
[
https://lh3.googleusercontent.com/2nPXgKhjFiG8S9uTa2TTXP1-CcUjZnjdJ5CVAd3_f…]
[Une image contenant texte, clipart Description générée automatiquement]
+33 4 28 29 37 63
[
https://lh6.googleusercontent.com/hGLtorzP2LwpWN7a7qPxHUf-Ufq7UmoJXpduyzZWG…]
________________________________
De : Idir Benouaret <idir.benouaret(a)epita.fr>
Envoyé : jeudi 5 octobre 2023 16:16
À : current(a)ml.lre.epita.fr <current(a)ml.lre.epita.fr>
Cc : Nicolas Boutry <nicolas.boutry(a)epita.fr>
Objet : [Permanents] [Current] Séminaire Axe ML et Applications
Bonjour,
Dans le cadre des séminaires de l'axe ML et applications, je vous annonce que le
prochain séminaire sera donné par Behrooz Omidvar-Tehrani (
http://omidvar.info/),
chercheur à Amazon AI labs en Californie.
Ci-dessous, le titre et l'abstract du talk ainsi qu'une mini bio du présentateur.
Merci de bien vouloir remplir le framadate suivant :
https://framadate.org/wWW99oIRX3syHien
Avant le mardi 10 octobre, afin de fixer la date pour cet évènement.
Ps. Je ne peux proposer plus de dates et d'horaires à cause des contraintes du
présentateur et du décalage horaire
----------------------------------------------------------------------------------
Title: Guided Text-based Item Exploration
Speaker: Behrooz Omidvar-Tehrani, Amazon AWS AI Labs
Abstract: Users in their different roles (data owners, customers, stakeholders,
advertisers) interact with data systems to seek information. Typical information seeking
paradigms such as search and recommendation, depend on a crystal-clear definition of an
information seeking task to operate. In reality, most data-centric tasks are subjective
which require a sequence of interactions to manifest and clarify. Interacting with data
systems is a tedious task and users need to receive guided recommendations from the system
to optimize their interactions when dealing with subjectivity. In this talk, we focus on
the challenge of "subjective needs" and "multi-shot tasks", and review
(1) how the diverse and heterogeneous set of user interactions can be formalized and
represented in the form of a unique model, and (2) how data systems can leverage the
interaction model to assist users in their interactions by disambiguating their needs and
guiding users through their information seeking journey until landing on their ideal
target. We discuss real-world use cases of formalizing and learning interactions, both in
academia and industry, whose core objective is to help users interact with data systems
more effectively. We also discuss future directions of interaction learning, such as
incorporating domain knowledge and multi-environment exploration.
Speaker Bio: Behrooz is an Applied Scientist in AWS AI Labs. Prior to Amazon, he held
positions in Naver Labs Europe, the Grenoble Alpes University, and the Ohio State
University. He received his PhD in CS from the University of Grenoble Alpes, France, in
2015. His research focuses on Human-in-the-Loop Data Analytics spanning over different
research areas such as Data Mining, Databases, Visual Analytics, and Machine Learning. He
has published more than 40 papers in top-ranked international conferences and journals
including VLDB, SIGMOD, CIKM, TKDE, and CHI.
En vous remerciant,
Idir
[Une image contenant texte, clipart, signe Description générée automatiquement]
Idir Benouaret
Enseignant-Chercheur
[
https://lh6.googleusercontent.com/dCYVl9pmYNgg1wBndkYtELRR9DX8RRY5d_e4N2Xhk…]
[
https://lh4.googleusercontent.com/O8lm18dZZ188g_iBNOmO2UX8qPx8zNmCfFbItUDzk…]
[
https://lh4.googleusercontent.com/iJejRKKnVTGA2lyz-eMOKQvI9vVP-ftzUIqzCoeoR…]
[
https://lh6.googleusercontent.com/J3eMugeLIjhhZigE4aw44kR3o5SCCOf3J7YJfPDTC…]
[
https://lh3.googleusercontent.com/2nPXgKhjFiG8S9uTa2TTXP1-CcUjZnjdJ5CVAd3_f…]
[Une image contenant texte, clipart Description générée automatiquement]
+33 4 28 29 37 63
[
https://lh6.googleusercontent.com/hGLtorzP2LwpWN7a7qPxHUf-Ufq7UmoJXpduyzZWG…]
______________________
Current mailing list -- current(a)ml.lre.epita.fr
https://lists.lrde.epita.fr/postorius/lists/current.ml.lre.epita.fr//
______________________
Postdocs mailing list -- postdocs(a)ml.lre.epita.fr
https://lists.lrde.epita.fr/postorius/lists/postdocs.ml.lre.epita.fr//