ACL 2019 Announces Best Papers; Nature Covers Tianjic Chip; Baidu Releases ERNIE 2.0

Published in

SyncedReview

3 min readAug 4, 2019

Subscribe to Synced Global AI Weekly

ACL 2019 | Best Papers Announced
The Association for Computational Linguistics (ACL) held its 57th annual meeting July 28 to August 2 in Florence, Italy. The ACL 2019 organizing committee announced its eight paper awards: Best Long Paper, Best Short Paper, Best Demo Paper, and five Outstanding Paper awards.
(Synced)

Nature Cover Story | Chinese Team’s ‘Tianjic Chip’ Bridges Machine Learning and Neuroscience in Pursuit of AGI
Respected scientific journal Nature boosted the case for AGI with a cover story on a new research paper, Towards artificial general intelligence with hybrid Tianjic chip architecture, which aims to stimulate AGI development by adopting generalized hardware platforms.
(Synced) / (Nature)

Baidu’s ERNIE 2.0 Beats BERT and XLNet on NLP Benchmarks
The updated ERNIE 2.0 model outperforms BERT and the recent XLNet (a generalized autoregressive pretraining model) on 16 tasks including English GLUE benchmarks and various Chinese language tasks.
(Synced) / (Baidu) / (GitHub)

Technology

∂P: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
Researchers describe a Differentiable Programming (∂P) system that is able to take gradients of Julia programs making Automatic Differentiation a first class language feature. This system supports almost all language constructs and compiles high-performance code without requiring any user intervention or refactoring to stage computations.
(Julia Computing & MIT & Invenia Labs)

DeepMind Using AI to Give Doctors a 48-Hour Head Start on Life-Threatening Illness
Researchers develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records and using acute kidney injury — a common and potentially life-threatening condition — as an exemplar.
(DeepMind) / (Nature)

On Mutual Information Maximization for Representation Learning
Researchers argue, and provide empirical evidence, that the success of these methods might be only loosely attributed to the properties of MI, and that they strongly depend on the inductive bias in both the choice of feature extractor architectures and the parametrization of the employed MI estimators.
(Google Research)