Modelling Radiological Language with Bidirectional Long Short-Term Memory Networks

Savelie Cornegruta, Robert Bakewell, Samuel Withey, Giovanni Montana*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

27 Citations (Scopus)

Abstract

Motivated by the need to automate medical information extraction from free-text radiological reports, we present a bi-directional long short-term memory (BiLSTM) neural network architecture for modelling radiological language. The model has been used to address two NLP tasks: medical named-entity recognition (NER) and negation detection. We investigate whether learning several types of word embeddings improves BiLSTM's performance on those tasks. Using a large dataset of chest x-ray reports, we compare the proposed model to a baseline dictionary-based NER system and a negation detection system that leverages the hand-crafted rules of the NegEx algorithm and the grammatical relations obtained from the Stanford Dependency Parser. Compared to these more traditional rule-based systems, we argue that BiLSTM offers a strong alternative for both our tasks.

Original languageEnglish
Title of host publicationEMNLP 2016 - 7th International Workshop on Health Text Mining and Information Analysis, LOUHI 2016 - Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages17-27
Number of pages11
ISBN (Electronic)9781945626333
Publication statusPublished - 2016
EventEMNLP 2016 7th International Workshop on Health Text Mining and Information Analysis, LOUHI 2016 - Austin, United States
Duration: 5 Nov 2016 → …

Publication series

NameEMNLP 2016 - 7th International Workshop on Health Text Mining and Information Analysis, LOUHI 2016 - Proceedings of the Workshop

Conference

ConferenceEMNLP 2016 7th International Workshop on Health Text Mining and Information Analysis, LOUHI 2016
Country/TerritoryUnited States
CityAustin
Period5/11/2016 → …

Fingerprint

Dive into the research topics of 'Modelling Radiological Language with Bidirectional Long Short-Term Memory Networks'. Together they form a unique fingerprint.

Cite this