Gemini: A Family of Highly Capable Multimodal Models

Gemini Robotics Team, Rohan Anil, Sebastian Borgeaud, +741

arXiv (Cornell University)

Artificial IntelligenceNatural Language ProcessingNew FamilyLarge Ai ModelImage Analysis +13

Simple, Scalable Adaptation for Neural Machine Translation

Ankur Bapna

Natural Language ProcessingApplied LinguisticsEngineeringMachine LearningComputational Linguistics +12

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

Naveen Arivazhagan, Ankur Bapna, Dmitry Lepikhin, +9

arXiv (Cornell University)

EngineeringMachine LearningCross-lingual RepresentationMultilingualismMultilingual Pretraining +15

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

Yanping Huang, Youlong Cheng, Ankur Bapna, +7

arXiv (Cornell University)

Multiple AcceleratorsConvolutional Neural NetworkEngineeringMachine LearningComputer Architecture +14

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Jonathan Shen, Patrick Nguyen, Yonghui Wu, +87

arXiv (Cornell University)

EngineeringMachine LearningTensorflow FrameworkAi FoundationQuantized Inference +14

Building a Conversational Agent Overnight with Dialogue Self-Play

Pararth Shah, Dilek Hakkani‐Tür, Gökhan Tür, +4

arXiv (Cornell University)

Artificial IntelligenceEngineeringDialogue System DeveloperSpoken Dialog SystemIntelligent Systems +20

Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets

Julia Kreutzer, Isaac Caswell, Lisa Wang, +47

Transactions of the Association for Computational Linguistics

Web-crawled Multilingual DatasetsEngineeringCross-lingual RepresentationMultilingualismMultilingual Pretraining +20

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model

Anjuli Kannan, Arindrima Datta, Tara N. Sainath, +6

EngineeringMachine LearningMultilingualismSpoken Language ProcessingCorpus Linguistics +15

Training Deeper Neural Machine Translation Models with Transparent Attention

Ankur Bapna, Mia Chen, Yuan Cao, +1

Natural Language ProcessingMultimodal LlmLarge Ai ModelEngineeringMachine Learning +11

FLEURS: FEW-Shot Learning Evaluation of Universal Representations of Speech

Alexis Conneau, Min Ma, Simran Khanuja, +6

2022 IEEE Spoken Language Technology Workshop (SLT)

Few-shot LearningEngineeringMachine LearningMultilingual PretrainingLow-resource Language Processing +15