Benoît Sagot Profile
Benoît Sagot

@bensagot

Followers
641
Following
164
Media
3
Statuses
130

Joined January 2012
Don't wanna be here? Send us removal request.
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
10 months
The ALMAnaCH project-team at Inria Paris is now on an alternative platform (same username, i.e. inriaparisnlp)! Follow us there for news and updates about our research and seminar announcements!
0
1
4
@cdf1530
Collège de France
1 year
🕘 Retour sur l'année du Collège de France ! 💬 "Apprendre les langues aux machines" 🖥️ Retrouvez la leçon inaugurale de @BenSagot, professeur invité sur la chaire annuelle #Informatique et sciences numériques en partenariat avec @Inria. 👉 https://t.co/j4WNEKAJw3
1
17
28
@FuteralMatthieu
Matthieu Futeral-Peter
1 year
Announcing mOSCAR, multilingual interleaved text-image corpus as part of @oscarnlp project. Paper: https://t.co/1hhnyYCyI3 Dataset: https://t.co/hiEUJ1Q3iJ Doc: https://t.co/KsnT5wVee2 1/6
3
27
54
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
1 year
We are thrilled to announce our next seminar, co-organised w/ @ISIR_labo. Nicolas Rollet (@telecomparis) will be talking about “Interaction Humain-Machine, IA parlante et ethnométhodologie : le diable est dans les détails”, Friday 21/6, 11am CEST. Details➡️ https://t.co/pPbWfkALM4
1
3
6
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
1 year
🏆Best student paper award at #LRECCOLING2024! Congratulations to @BafnaNiyati (@jhuclsp), co-supervised by @bensagot & @RABawden (from @inria_paris & @InstitutPrairie) and Cristina España-Bonet & Josef van Genabith (from @DFKI)
2
9
53
@nthngdy
Nathan Godey
2 years
🤏 Why do small Language Models underperform? We prove empirically and theoretically that the LM head on top of language models can limit performance through the softmax bottleneck phenomenon, especially when the hidden dimension <1000. 📄Paper: https://t.co/YkdQttDDSK (1/10)
17
124
606
@EditionsCdF
Éditions du Collège de France
2 years
[#Parution] Benoît Sagot, “Apprendre les #langues aux machines”, @EditionsCdF, coll. “Leçons inaugurales”, en librairie à partir d’aujourd’hui https://t.co/hFdOTEqaUz @lcdpu @cdf1530 @bensagot #apprentissage #IA #chatGPT #informatique
0
5
15
@EditionsCdF
Éditions du Collège de France
2 years
[À paraître] Benoît Sagot, “Apprendre les #langues aux machines”, @EditionsCdF, coll. “Leçons inaugurales”, en librairie à partir du 11 avril https://t.co/oFNResNebO @lcdpu @cdf1530 @bensagot #apprentissage #IA #chatGPT #informatique
0
5
9
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
🤩📄 We are delighted that 8 papers from the team have been accepted at @LrecColing 2024! Have a read through the titles and camera-ready versions here (in no particular order):
1
8
25
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
We're excited for the final seminar in the Collège de France series as part of @bensagot’s annual chair: 9/2/24 at 11am CET: Yann Le Cun, "L'IA axée sur les objectifs : vers des machines capables d'apprendre, de raisonner et de planifier" @ylecun @cdf1530 @AIatMeta @nyuniversity
2
15
41
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
We are really happy to announce the next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 02/02/24 at 11am CET: Philippe Blache (CNRS) on "Prédire c'est comprendre : un modèle neuro-cognitif du langage fondé sur la prédiction" @cdf1530 @CNRS
1
4
14
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
Next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 26/01/24 at 11am CET: Elena Cabrio on "Analyse automatique de l'argumentation dans les débats politiques" @ECabrio @cdf1530 @Univ_CotedAzur @inria_sophia @Laboratoire_I3S @wimmics
1
9
18
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
We are excited to announce the next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 19/01/24 at 11am CET: @ClaireGardent on "Génération de texte à partir de connaissances" @cdf1530 @CNRS @synalp_nancy @labo_Loria @Univ_Lorraine
1
5
9
@nthngdy
Nathan Godey
2 years
Really excited to announce that our Headless Language Models paper has been accepted at #ICLR2024 ! See you in Vienna 🇦🇹 Paper link: https://t.co/KwNqdNAswo @InriaParisNLP @bensagot @DeVillemonte
@nthngdy
Nathan Godey
2 years
🔥 New pretraining method 🔥 Our models learn to recover masked input embeddings instead of predicting masked input tokens. It leads to substantial improvements and efficiency gains for encoder AND decoder models. 🗞️ Paper: https://t.co/ByummSfMe9 🧵 below
5
11
38
@InriaParisNLP
Inria Paris NLP (ALMAnaCH team)
2 years
We are thrilled to announce the 2nd seminar in the Collège de France series (as part of @bensagot’s annual chair position): 15/12/23 at 11am CET: Guillaume Jacques (@rgyalrong) on “Deux exemples d’usage des transducteurs en linguistique”. @cdf1530 @CNRS @EPHE_PSL
1
7
12
@cdf1530
Collège de France
2 years
#Science #IA "Apprendre les langues aux machines" 🖥️ La vidéo de la leçon inaugurale de Benoît Sagot (@bensagot), professeur invité sur la chaire annuelle #Informatique et sciences numériques, est disponible. 👉 https://t.co/ya0EmKGsNc En partenariat avec @Inria.
0
4
13
@bensagot
Benoît Sagot
2 years
1
0
3