Arvind Neelakantan
University of Siena(IT)Boston College(US)University of Geneva(CH)DePaul University(US)Michigan Technological University(US)Google (United States)(US)Nuance Communications (Austria)(AT)University of Minnesota(US)Pennsylvania State University(US)American Jewish Committee(US)North Carolina State University(US)Rochester Institute of Technology(US)University of New Hampshire(US)University of Groningen(NL)University of Dundee(GB)Chinese University of Hong Kong(CN)University of California, Santa Cruz(US)Université d'Avignon et des Pays de Vaucluse(FR)University of Zurich(CH)University of Cambridge(GB)University of Michigan–Ann Arbor(US)University of Minnesota System(US)Eyegaze (United States)(US)École Normale Supérieure(BI)Google (United Kingdom)(GB)National Research Council Canada(CA)Bauhaus-Universität Weimar(DE)University of Virginia(US)Gallaudet University(US)Chalmers University of Technology(SE)Idiap Research Institute(CH)Columbia University(US)Eindhoven University of Technology(NL)Université Grenoble Alpes(FR)University of Sheffield(GB)Leipzig University(DE)University of Bologna(IT)Stanford University(US)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Multimodal Machine Learning Applications, Advanced Graph Neural Networks, Speech and dialogue systems
Most-Cited Works
- → Language Models are Few-Shot Learners(2020)3,027 cited
- → Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space(2014)461 cited
- → Adding Gradient Noise Improves Learning for Very Deep Networks(2015)265 cited
- → Compositional Vector Space Models for Knowledge Base Completion(2015)231 cited
- → Text and Code Embeddings by Contrastive Pre-Training(2022)148 cited
- → Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset(2019)138 cited
- → Neural Programmer: Inducing Latent Programs with Gradient Descent