Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: On Learning Language-Invariant Representations for Universal Machine Translation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-016-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-016-alpha.b-cdn.net
      • sl-yoda-v3-stream-016-beta.b-cdn.net
      • 1504562137.rsc.cdn77.org
      • 1896834465.rsc.cdn77.org
      • Subtitles
      • Off
      • en
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            On Learning Language-Invariant Representations for Universal Machine Translation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            On Learning Language-Invariant Representations for Universal Machine Translation

            Jul 12, 2020

            Speakers

            HZ

            Han Zhao

            Speaker · 0 followers

            JH

            Junjie Hu

            Speaker · 0 followers

            AR

            Andrej Risteski

            Speaker · 0 followers

            About

            The goal of universal machine translation is to learn to translate between any pair of languages, given pairs of translated documents for some of these languages. Despite impressive empirical results and an increasing interest in massively multilingual models, theoretical analysis on translation errors made by such universal machine translation models is only nascent. In this paper, we take one step towards better understanding of universal machine translation by first proving an impossibility t…

            Organizer

            I2
            I2

            ICML 2020

            Account · 210 followers

            Categories

            Linguistics & Philology

            Category · 88 presentations

            About ICML 2020

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
            14:34

            Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

            Ashley Edwards, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            DeBayes: a Bayesian method for debiasing network embeddings
            14:26

            DeBayes: a Bayesian method for debiasing network embeddings

            Maarten Buyl, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Probing Dynamic Environments with Informed Policy Regularization
            05:20

            Probing Dynamic Environments with Informed Policy Regularization

            Matteo Pirotta, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Graph Homomorphism Convolution
            16:07

            Graph Homomorphism Convolution

            Hoang Nguyen, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
            14:25

            Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks

            Marko Vasic, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Wandering Within a World: Online Contextualized Few-Shot Learning
            36:48

            Wandering Within a World: Online Contextualized Few-Shot Learning

            Richard Zemel, …

            I2
            I2
            ICML 2020 5 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow ICML 2020