Universal Language Model Fine-tuning for Text Classification

ACL 2018 37 code implementations

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.

LANGUAGE MODELLING SENTIMENT ANALYSIS TEXT CLASSIFICATION TRANSFER LEARNING

Attention-based Extraction of Structured Information from Street View Imagery

11 Apr 20172 code implementations

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%.

Deep Reinforcement Learning

15 Oct 20184 code implementations

We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.

Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction

18 Apr 20172 code implementations

CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.

CLICK-THROUGH RATE PREDICTION FEATURE ENGINEERING

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

3 Oct 20185 code implementations

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.

DECISION MAKING

Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce

7 Mar 20172 code implementations

In this paper, we present a unified end-to-end approach to build a large scale Visual Search and Recommendation system for e-commerce.

IMAGE RETRIEVAL

The autofeat Python Library for Automated Feature Engineering and Selection

22 Jan 20191 code implementation

This paper describes the autofeat Python library, which provides a scikit-learn style linear regression model with automated feature engineering and selection capabilities.

AUTOMATED FEATURE ENGINEERING FEATURE ENGINEERING REGRESSION

Predictive Business Process Monitoring with LSTM Neural Networks

7 Dec 20161 code implementation

First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp.

MULTIVARIATE TIME SERIES FORECASTING TIME SERIES PREDICTION

DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

13 Apr 20174 code implementations

Probabilistic forecasting, i. e. estimating the probability distribution of a time series' future given its past, is a key enabler for optimizing business processes.

TIME SERIES

MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization

12 Oct 20181 code implementation

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.

ABSTRACTIVE TEXT SUMMARIZATION