Using Alignments in Automatic Paraphrase Production to Combat Data Sparsity in Question Interpretation for a Virtual Patient Dialogue System

Loading...
Thumbnail Image

Date

2019-05

Journal Title

Journal ISSN

Volume Title

Publisher

The Ohio State University

Research Projects

Organizational Units

Journal Issue

Abstract

Automatic paraphrase generation is a task explored in many areas of natural language processing. In this study we attempt to use automatic paraphrasing to augment the training data for a virtual patient dialogue system. The system performs in-domain question answering in an attempt to replicate the function of standardized patients, and aid medical students in practicing their patient interviewing skills.

Description

Keywords

Natural Language Processing, Paraphrase Generation, Virtual Dialogue System, Virtual Patient, Patient Interview

Citation