J
Jakob Uszkoreit
Researcher at Google
Publications - 85
Citations - 83076
Jakob Uszkoreit is an academic researcher from Google. The author has contributed to research in topics: Machine translation & Transformer (machine learning model). The author has an hindex of 36, co-authored 84 publications receiving 37432 citations. Previous affiliations of Jakob Uszkoreit include University of California, Berkeley.
Papers
More filters
Posted Content
Object-Centric Learning with Slot Attention
Francesco Locatello,Dirk Weissenborn,Thomas Unterthiner,Aravindh Mahendran,Georg Heigold,Jakob Uszkoreit,Alexey Dosovitskiy,Thomas Kipf +7 more
TL;DR: The Slot Attention module as mentioned in this paper is an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention.
Patent
Auto-translation for multi user audio and video
Trausti Kristjansson,John Chih Chang Huang,Yu-Kuan Lin,Hung-ying Tyan,Jakob Uszkoreit,Joshua James Estelle,C.K. Wang,Kirill Buryak,Yusuke Konishi +8 more
TL;DR: In this article, a system, computer readable storage medium, and a method providing an audio and textual transcript of a communication is described, where conferencing services may receive audio or audio visual signals from a plurality of different devices that receive voice communications from participants in a communication, such as a chat or teleconference.
Proceedings Article
Watermarking the Outputs of Structured Prediction with an application in Statistical Machine Translation.
TL;DR: This work proposes a general method to watermark and probabilistically identify the structured outputs of machine learning algorithms and presents an application in statistical machine translation, where machine translated output is watermarked at minimal loss in translation quality and detected with high recall.
Proceedings Article
Language-Independent Discriminative Parsing of Temporal Expressions
Gabor Angeli,Jakob Uszkoreit +1 more
TL;DR: This work presents a language independent semantic parser for learning the interpretation of temporal phrases given only a corpus of utterances and the times they reference, making use of a latent parse that encodes a language-flexible representation of time.
Patent
Virtual participant-based real-time translation and transcription system for audio and video teleconferences
TL;DR: In this article, the authors describe a teleconferencing system that uses a virtual participant processor to translate language content of the teleconference into each participant's spoken language without additional user inputs.