Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.
#2 best model for Text Classification on TREC-6
We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84. 2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72. 46%.
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
In this paper, we present a unified end-to-end approach to build a large scale Visual Search and Recommendation system for e-commerce.
This paper describes the autofeat Python library, which provides a scikit-learn style linear regression model with automated feature engineering and selection capabilities.
Our proposed model consists of an auto-encoder where the mean of the representations of the input reviews decodes to a reasonable summary-review while not relying on any review-specific features.
First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp.