Adverse drug reaction classification with deep neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations Save citation

Open

Authors

Research units

Abstract

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.

Documents

Details

Publication date2016
Publication titleProceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Pages877–887
Number of pages11
Original languageEnglish
Event26th International Conference on Computational Linguistics - Osaka, Japan

Conference

Conference26th International Conference on Computational Linguistics
CountryJapan
CityOsaka
Period11/12/1616/12/16

Bibliographic note

This work is licensed under a Creative Commons Attribution 4.0 International Licence http://creativecommons.org/licenses/by/4.0/ Funding: EPSRC AMR4AMR project EP/M02735X/1).

Download statistics

No data available

Employable Graduates; Exploitable Research

Copy the text from this field...