conftrace_

2018 EMNLP EMNLP 2018

UZH@SMM4H: System Descriptions

Abstract

AbstractOur team at the University of Zürich participated in the first 3 of the 4 sub-tasks at the Social Media Mining for Health Applications (SMM4H) shared task. We experimented with different approaches for text classification, namely traditional feature-based classifiers (Logistic Regression and Support Vector Machines), shallow neural networks, RCNNs, and CNNs. This system description paper provides details regarding the different system architectures and the achieved results.

Authors

Tilia Ellendorff, Joseph Cornelius, Heath Gordon, Nicola Colic, Fabio Rinaldi

Topics

Machine Learning > Core Methods > Classification Deep Learning > Architectures > Neural Networks

Keywords

text classification logistic regression support vector machine convolutional neural network recurrent neural network social media mining

More from EMNLP 2018

All EMNLP 2018 papers →

IRISA at SMM4H 2018: Neural Network and Bagging for Tweet Classification

Drug-Use Identification from Tweets with Word and Character N-Grams

Automatic Identification of Drugs and Adverse Drug Reaction Related Tweets

Deep Learning for Social Media Health Text Classification

Using PPM for Health Related Text Detection

Leveraging Web Based Evidence Gathering for Drug Information Identification from Tweets