DeepAI AI Chat
Log In Sign Up

COVCOR20 at WNUT-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules

by   Ali Hürriyetoğlu, et al.
Koç University
Radboud Universiteit

In the scope of WNUT-2020 Task 2, we developed various text classification systems, using deep learning models and one using linguistically informed rules. While both of the deep learning systems outperformed the system using the linguistically informed rules, we found that through the integration of (the output of) the three systems a better performance could be achieved than the standalone performance of each approach in a cross-validation setting. However, on the test data the performance of the integration was slightly lower than our best performing deep learning model. These results hardly indicate any progress in line of integrating machine learning and expert rules driven systems. We expect that the release of the annotation manuals and gold labels of the test data after this workshop will shed light on these perplexing results.


page 1

page 2

page 3

page 4


Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI

A novel deep learning architecture (XmasNet) based on convolutional neur...

RMDL: Random Multimodel Deep Learning for Classification

The continually increasing number of complex datasets each year necessit...

Computer-Assisted Creation of Boolean Search Rules for Text Classification in the Legal Domain

In this paper, we present a method of building strong, explainable class...

NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep

Existing Machine Learning techniques yield close to human performance on...

Rethinking annotation granularity for overcoming deep shortcut learning: A retrospective study on chest radiographs

Deep learning has demonstrated radiograph screening performances that ar...

Symbolic integration by integrating learning models with different strengths and weaknesses

Integration is indispensable, not only in mathematics, but also in a wid...

Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs

Background: Twelve lead ECGs are a core diagnostic tool for cardiovascul...