Search Results
Coreference Resolution through a seq2seq Transition-Based System
google-research/google-research
•
•
We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83. 3 F1-score for English (a 2. 3 higher F1-score than previous work (Dobrovolskii, 2021)) using only CoNLL data for training, 68. 5 F1-score for Arabic (+4. 1 higher than previous work) and 74. 3 F1-score for Chinese (+5. 3).
Ranked #1 on
Coreference Resolution
on OntoNotes
Revisiting Neural Scaling Laws in Language and Vision
google-research/google-research
•
•
The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longer schedules.
Efficient and Stable Fully Dynamic Facility Location
google-research/google-research
•
•
We consider the classic facility location problem in fully dynamic data streams, where elements can be both inserted and deleted.
Data Structures and Algorithms
Dichotomy of Control: Separating What You Can Control from What You Cannot
google-research/google-research
•
•
While return-conditioning is at the heart of popular algorithms such as decision transformer (DT), these methods tend to perform poorly in highly stochastic environments, where an occasional high return can arise from randomness in the environment rather than the actions themselves.
Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation
google-research/google-research
•
•
If one sees the place name Houston Mercer Dog Run in New York, how does one know how to pronounce it?
Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT
google-research/google-research
•
•
We combine the capacity of sparsely gated Mixture-of-Experts (MoE) with the speed and stability of linear, mixing transformations to design the Sparse Mixer encoder model.
An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
google-research/google-research
•
•
Then, we extensively evaluate three classes of Edge TPUs, covering different computing ecosystems, that are either currently deployed in Google products or are the product pipeline, across 423K unique convolutional neural networks.
Scaling Forward Gradient With Local Losses
google-research/google-research
•
•
Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks.
A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systems
google-research/google-research
•
•
We believe that this novel methodology for ML development can be demonstrated through a modularized representation of ML models and the definition of novel abstractions allowing to implement and execute diverse methods for the asynchronous use and extension of modular intelligent systems.
Ranking Neural Checkpoints
google-research/google-research
•
•
CVPR 2021
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task.
