Toward a Neural Semantic Parsing System for EHR Question Answering

TL;DR

This paper evaluates neural semantic parsing models for electronic health record question answering, demonstrating promising results and analyzing common errors to guide future improvements in clinical NLP applications.

Contribution

It systematically assesses the performance of neural semantic parsing models for EHR question answering, highlighting their potential and identifying areas for enhancement.

Findings

Neural models show promising performance on clinical SP datasets.

Ease of application and generalizability of neural models are advantageous.

Error analysis reveals common mistake types to inform future research.

Abstract

Clinical semantic parsing (SP) is an important step toward identifying the exact information need (as a machine-understandable logical form) from a natural language query aimed at retrieving information from electronic health records (EHRs). Current approaches to clinical SP are largely based on traditional machine learning and require hand-building a lexicon. The recent advancements in neural SP show a promise for building a robust and flexible semantic parser without much human effort. Thus, in this paper, we aim to systematically assess the performance of two such neural SP models for EHR question answering (QA). We found that the performance of these advanced neural models on two clinical SP datasets is promising given their ease of application and generalizability. Our error analysis surfaces the common types of errors made by these models and has the potential to inform future research into improving the performance of neural SP models for EHR QA.