Adverse drug reaction classification with deep neural networks


We study the problem of detecting sentences describing adverse drug reactions (ADRs) and frame the problem as binary classification. We investigate different neural network (NN) architectures for ADR classification. In particular, we propose two new neural network models, Convolutional Recurrent Neural Network (CRNN) by concatenating convolutional neural networks with recurrent neural networks, and Convolutional Neural Network with Attention (CNNA) by adding attention weights into convolutional neural networks. We evaluate various NN architectures on a Twitter dataset containing informal language and an Adverse Drug Effects (ADE) dataset constructed by sampling from MEDLINE case reports. Experimental results show that all the NN architectures outperform the traditional maximum entropy classifiers trained from n-grams with different weighting strategies considerably on both datasets. On the Twitter dataset, all the NN architectures perform similarly. But on the ADE dataset, CNN performs better than other more complex CNN variants. Nevertheless, CNNA allows the visualisation of attention weights of words when making classification decisions and hence is more appropriate for the extraction of word subsequences describing ADRs.

Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
?? 50811700Jl ??
Additional Information: This work is licensed under a Creative Commons Attribution 4.0 International Licence Funding: EPSRC AMR4AMR project EP/M02735X/1).
Event Title: 26th International Conference on Computational Linguistics
Event Type: Other
Event Dates: 2016-12-11 - 2016-12-16
Last Modified: 20 May 2024 07:47
Date Deposited: 20 Dec 2016 16:25
Full Text Link: http://www.aclw ... 16/C16-1084.pdf
Related URLs:
PURE Output Type: Conference contribution
Published Date: 2016-12-16
Accepted Date: 2016-12-01
Authors: Huynh, Trung
He, Yulan (ORCID Profile 0000-0003-3948-5845)
Willis, Allistair
Rueger, Stefan



Version: Accepted Version

License: Creative Commons Attribution

Export / Share Citation


Additional statistics for this record