Where's the Question? A Multi-channel Deep Convolutional Neural Network for Question Identification in Textual Data

TL;DR

This paper introduces Quest-CNN, a multi-channel deep convolutional neural network designed to accurately identify real questions in clinical dialogues, outperforming traditional methods and other neural networks in both domain-specific and general datasets.

Contribution

The study presents a novel multi-channel deep CNN architecture, Quest-CNN, specifically tailored for question identification in clinical dialogue data, demonstrating superior performance over existing methods.

Findings

Quest-CNN achieved the highest F1 scores on clinical and general datasets.

It outperformed traditional rule-based and learning-based question detection methods.

The model effectively distinguishes real questions from non-questions and c-questions.

Abstract

In most clinical practice settings, there is no rigorous reviewing of the clinical documentation, resulting in inaccurate information captured in the patient medical records. The gold standard in clinical data capturing is achieved via "expert-review", where clinicians can have a dialogue with a domain expert (reviewers) and ask them questions about data entry rules. Automatically identifying "real questions" in these dialogues could uncover ambiguities or common problems in data capturing in a given clinical setting. In this study, we proposed a novel multi-channel deep convolutional neural network architecture, namely Quest-CNN, for the purpose of separating real questions that expect an answer (information or help) about an issue from sentences that are not questions, as well as from questions referring to an issue mentioned in a nearby sentence (e.g., can you clarify this?), which we will refer as "c-questions". We conducted a comprehensive performance comparison analysis of the proposed multi-channel deep convolutional neural network against other deep neural networks. Furthermore, we evaluated the performance of traditional rule-based and learning-based methods for detecting question sentences. The proposed Quest-CNN achieved the best F1 score both on a dataset of data entry-review dialogue in a dialysis care setting, and on a general domain dataset.