Results 11 to 20 of about 107 (95)

Multilingual Mathematical Autoformalization

CoRR, 2023
Autoformalization is the task of translating natural language materials into machine-verifiable formalisations. Progress in autoformalization research is hindered by the lack of a sizeable dataset consisting of informal-formal pairs expressing the same essence.
Albert Q. Jiang, Wenda Li, Mateja Jamnik
openaire   +3 more sources

Autoformalization with Large Language Models

Advances in Neural Information Processing Systems 35, 2022
Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs. A successful autoformalization system could advance the fields of formal verification, program synthesis, and artificial intelligence.
Wu, Yuhuai, Jiang, Qiaochu, Li, Wenda, Rabe, Markus, Staats, Charles, Jamnik, Mateja, Szegedy, Christian   +6 more
openaire   +5 more sources

A New Approach Towards Autoformalization

CoRR, 2023
Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a program. This is a challenging task, and especially for higher-level mathematics found in research papers.
Nilay Patel, Rahul Saha, Jeffrey Flanigan   +2 more
openaire   +3 more sources

AutoFormer: Searching Transformers for Visual Recognition [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding dimension, and number of heads can largely affect the performance of vision transformers.
Minghao Chen, Houwen Peng, Jianlong Fu, Haibin Ling   +3 more
openaire   +3 more sources

Autoformation, autonomisation et émancipation : [PDF]

Recherches & éducations, 2016
Les recherches sur l’autoformation, en français comme en anglais, ont développé un champ conceptuel riche où les notions d’autonomie et d’émancipation sont parfois confondues, dans leur acception originelle, même si l’histoire des différents courants de recherche a ensuite emprunté différentes voies d’interprétation. Ces recherches ont ainsi abordé des
openaire   +2 more sources

Bibliothèques et autoformation [PDF]

, 2006
Dans un univers où les nouvelles technologies évoluent constamment et où l'individu est régulièrement amené à se recycler dans sa carrière professionnelle ou à maîtriser les outils de développement personnel, la bibliothèque est aujourd'hui le lieu d'expression d'une demande nouvelle en autoformation. Cette demande, dépendante pour partie de l'offre de
Gérald Grunberg, Thierry Grognet, Philippe Carré, Pascaline Blandin, Joëlle Muller, Reza Ebrahimi, Martine Blanc-Montmayeur, Anne Jay, Brian Gambles, Pierre Verbeke, Chérif Lounici, Michel Fauchié, Marion Lhuillier, Sylviane Brunel, Florence Couvreur-Neu, Bernard Blandin, Agnès Camus-Vigué   +16 more
openaire   +1 more source

L'Autoformation continue, signification et voies possibles

Canadian Journal of Education, 1983
Quelle signification revêt le concept d'autoformation sinon celle de continuité ou d'interaction entre les deux moments de la carrière active de l'enseignant, à savoir: formation initiale et formation continue.
Cécile Touzin-St-Pierre
doaj   +6 more sources

Défis associés à l’élaboration d’une autoformation numérique pour apprendre à enseigner la syntaxe et la ponctuation

Language and Literacy: A Canadian Educational e-journal
L’accès à des formations de qualité en éducation est parfois restreint pour des raisons financières ou logistiques. La multiplication des outils numériques facilite toutefois l’accès à de meilleures formations à distance.
Marie-Hélène Giguère, Claude Quevillon Lacasse   +1 more
doaj   +1 more source

Autoformalizing Euclidean Geometry

CoRR
Autoformalization involves automatically translating informal math into formal theorems and proofs that are machine-verifiable. Euclidean geometry provides an interesting and controllable domain for studying autoformalization. In this paper, we introduce a neuro-symbolic framework for autoformalizing Euclidean geometry, which combines domain knowledge,
Logan Murphy, Kaiyu Yang, Jialiang Sun, Zhaoyu Li, Anima Anandkumar, Xujie Si   +5 more
openaire   +3 more sources

Autoformalizer with Tool Feedback

CoRR
Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language models to training an end-to-end formalizer model from scratch, achieving remarkable advancements.
Qi Guo, Jianing Wang, Jianfei Zhang, Deyang Kong, Xiangzhou Huang, Xiangyu Xi, Wei Wang 0225, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye 0004   +10 more
openaire   +3 more sources