event-icon
Description

Programmatic Theme: Clinical Research Informatics

Abstract: In this paper, we investigate the task of spatial role labeling for extracting spatial relations from chest X-ray reports. Previous works have shown the usefulness of incorporating syntactic information in extracting spatial relations. We propose syntax-enhanced word representations in addition to word and character embeddings for extracting radiology- specific spatial roles. We utilize a bidirectional long short-term memory (Bi-LSTM) conditional random field (CRF) as the baseline model to capture the word sequence and employ additional Bi-LSTMs to encode syntax based on dependency tree substructures. Our focus is on empirically evaluating the contribution of each syntax integration method in extracting the spatial roles with respect to a SPATIAL INDICATOR in a sentence. The incorporation of syntax embeddings to the baseline method achieves promising results, with improvements of 1.3, 0.8, 4.6, and 4.6 points in the average F1 measures for TRAJECTOR, LANDMARK, DIAGNOSIS, and HEDGE roles, respectively.

Learning Objective: This paper conducts an empirical evaluation of incorporating different syntax encoding methods at the word level in addition to word and character embeddings for spatial relation extraction from radiology reports.

Authors:

Surabhi Datta (Presenter)
THE UNIVERSITY OF TEXAS HEALTH SCIENCE CENTER HOUSTON

Kirk Roberts, THE UNIVERSITY OF TEXAS HEALTH SCIENCE CENTER HOUSTON

Keywords, Themes & Types