You are here: Home / Research / Projects / Current / TransPHorm: Translation of Public Health Information for a Diverse Public

TransPHorm: Translation of Public Health Information for a Diverse Public

NWCPHP researchers are studying how to use machine translation technology to produce efficient and accurate public health material for limited English speakers as part of the TransPHorm project.

Researchers at TransPHorm are investigating the use of machine translation technology to shorten the time and costs of translating public health materials. The end goal of this research is to improve access to health information within limited English proficiency (LEP) populations.

TransPHorm project logo for machine translationFor people with limited English proficiency—more than 46 million people in the US—accurate, easy-to-understand health information is hard to access. It has been difficult for health departments to meet growing demands for multi-lingual health materials, due in part to the time and resources it takes to create high-quality translations.

Machine translation, or the translation of text into another language by a fully automatic computer program, holds promise for producing translations efficiently and accurately. However, to date, the quality of automated translations for public health materials has been poor.

TransPHorm project researchers have been working with bilingual health professionals at the Washington State Department of Health, University of Washington, Public Health - Seattle & King County, and local health departments to advance the understanding of current translation processes, and to examine how novel machine translation technologies can be incorporated into public health practice.

Specifically, researchers:

  • Use qualitative methods to understand current manual translation workflow and the time and costs involved with creating quality translations
  • Apply cognitive work analysis to describe the strengths and weaknesses of translation activities in public health
  • Investigate novel technologies for improving development and access to multilingual health information for limited English proficiency groups.
  • Systematically compare machine translation with manual translations in terms of quality, turnaround time and costs

This research is funded by a five-year grant from the National Library of Medicine.

Project period: September 30, 2011 to October 1, 2016

Research Team

Anne Turner, MD, MLIS, MPH
Principal Investigator

Katrin Kirchhoff, PhD
Principal Investigator

Hilary Karasz, PhD
Public Health - Seattle & King County Co-Investigator

Kristin Dew, MS
Research Coordinator

Loma Desai
Research Assistant

Daniel Capurro, MD, PhD
Assistant Professor

Tishra Beeson, MPH
Research Coordinator

Megumu Brownstein, MSW, MPH
Research Coordinator

Adrian Laurenzi
Research Assistant

Hannah Mandel
Research Assistant

Publications & Products

A Comparison of Human and Machine Translation of Health Promotion Materials for Public Health Practice: Time, Costs, and Quality
Academic Article, Journal of Public Health Management and Practice

Local Health Department Translation Processes: Potential of Machine Translation Technologies to Help Meet Needs
AMIA Annual Symposium Proceedings

Exploring Local Public Health Workflow in the Context of Automated Translation Technologies
AMIA Annual Symposium Proceedings

Exploring Local Public Health Work in the Context of Novel Translation Technologies
Academic Article: Studies in Health Technology and Informatics

A Conjoint Analysis Framework for Evaluating User Preferences in Machine Translation
Academic Article, Machine Translation

A Web-Based Collaborative Translation Management System for Public Health Workers
Conference Proceedings, Computer Human Interaction

Evaluating User Preferences in Machine Translation Using Conjoint Analysis
Conference Proceedings, European Association of Machine Translation

Using Crowdsourcing Technology for Testing Multilingual Public Health Promotion Materials
Academic Article, Journal of Medical Internet Research

Application of Statistical Machine Translation to Public Health Information: A Feasibility Study
Academic Article, Journal of the American Medical Informatics Association

Related Content

Translation Please? Improving Access to Health Information

TransPHorm: Translation for Public Health Information