Retrieving and reading: A comprehensive survey on open-domain question answering

F Zhu, W Lei, C Wang, J Zheng, S Poria… - ar** predictive models includes many stages. Most resources focus
on the modeling algorithms but neglect other critical aspects of the modeling process. This …

Epidemiological data from the COVID-19 outbreak, real-time case information

B Xu, B Gutierrez, S Mekaru, K Sewalk, L Goodwin… - Scientific data, 2020 - nature.com
Cases of a novel coronavirus were first reported in Wuhan, Hubei province, China, in
December 2019 and have since spread across the world. Epidemiological studies have …

Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey

G Nguyen, S Dlugolinsky, M Bobák, V Tran… - Artificial Intelligence …, 2019 - Springer
The combined impact of new computing resources and techniques with an increasing
avalanche of large datasets, is transforming many research areas and may lead to …

Feature selection in machine learning: A new perspective

J Cai, J Luo, S Wang, S Yang - Neurocomputing, 2018 - Elsevier
High-dimensional data analysis is a challenge for researchers and engineers in the fields of
machine learning and data mining. Feature selection provides an effective way to solve this …

Advances in pre-training distributed word representations

T Mikolov, E Grave, P Bojanowski, C Puhrsch… - arxiv preprint arxiv …, 2017 - arxiv.org
Many Natural Language Processing applications nowadays rely on pre-trained word
representations estimated from large text corpora such as news collections, Wikipedia and …

Hash layers for large sparse models

S Roller, S Sukhbaatar… - Advances in Neural …, 2021 - proceedings.neurips.cc
We investigate the training of sparse layers that use different parameters for different inputs
based on hashing in large Transformer models. Specifically, we modify the feedforward …