Skip to main content Accessibility help
×
Hostname: page-component-78c5997874-t5tsf Total loading time: 0 Render date: 2024-10-31T23:20:01.120Z Has data issue: false hasContentIssue false

Contents

Published online by Cambridge University Press:  31 August 2023

Meng Ji
Affiliation:
University of Sydney
Pierrette Bouillon
Affiliation:
Université de Genève
Mark Seligman
Affiliation:
Spoken Translation Technology

Summary

Type
Chapter
Information
Publisher: Cambridge University Press
Print publication year: 2023
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NC
This content is Open Access and distributed under the terms of the Creative Commons Attribution licence CC-BY-NC 4.0 https://creativecommons.org/cclicenses/

Contents

  1. Contributors

  2. Introduction

    1. Accessible Health Translation Technology Matters

    2. I-D-E-A: Principles of Accessible Health Translation Technology

      1. Detectability of Machine Translation Errors to Boost User Confidence

    3. Adaptability or Customizability

    4. Inclusivity to Serve People of Disability

    5. Equality of Accessibility Standards for Localized Multilingual Websites

  3. 1Speech and Translation Technologies: Explanations

    1. 1.1Introduction

    2. 1.2Automatic Speech Recognition

      1. 1.2.1Classical Automatic Speech Recognition

      2. 1.2.2Neural Automatic Speech Recognition

      3. 1.2.3Automatic Speech Recognition Issues and Directions

    3. 1.3Speech Synthesis (Text-to-Speech)

      1. 1.3.1Classical Text-to-Speech

      2. 1.3.2Neural Text-to-Speech

    4. 1.4Machine Translation

      1. 1.4.1Machine Translation Based on Fixed Phrases

      2. 1.4.2Full Machine Translation: Beyond Fixed Phrases

        1. 1.4.2.1Rule-Based Machine Translation

        2. 1.4.2.2Statistical Machine Translation

        3. 1.4.2.3Neural Machine Translation

    5. 1.5Conclusion

  4. 2Speech and Translation Technologies: Healthcare Applications

    1. 2.1Introduction

    2. 2.2Obstacles to Adoption and Potential Solutions

      1. 2.2.1Reliability

        1. 2.2.1.1Offline Preparation of Output

        2. 2.2.1.2Feedback

        3. 2.2.1.3Correction

        4. 2.2.1.4Record-Keeping

      2. 2.2.2Customization per Use Case

        1. 2.2.2.1Platforms

        2. 2.2.2.2Peripherals

        3. 2.2.2.3Security

    3. 2.3Speech Translation Designs for Healthcare

      1. 2.3.1Phrase-Based Speech Translation for Healthcare

        1. 2.3.1.1S-MINDS and Phraselator

        2. 2.3.1.2BabelDr

      2. 2.3.2Full Speech-to-Speech Translation for Healthcare

        1. 2.3.2.1Converser for Healthcare

        2. 2.3.2.2Fujitsu’s Focus on Ergonomics

    4. 2.4Past and Current Speech Translation Systems

      1. 2.4.1Reliability of Machine Translation for Healthcare: A Study

      2. 2.4.2Surveys of Speech Translation Systems

        1. 2.4.2.1Some Bi-directional Speech Translation Systems

        2. 2.4.2.2Some Phrase-Based Speech Translation Systems

        3. 2.4.2.3Fifteen Representative Apps: A Study

        4. 2.4.2.4Some Additional Links

    5. 2.5Conclusions

  5. 3Predicting Errors in Google Translations of Online Health Information

    1. 3.1Introduction

    2. 3.2Methods

      1. 3.2.1Research Hypothesis

      2. 3.2.2Screening Criteria for Text

      3. 3.2.3Topics of Infectious Diseases

      4. 3.2.4Labeling of Machine Translations

      5. 3.2.5Conceptual Mistakes in Machine Translations

      6. 3.2.6Prevalence of Conceptual Mistakes in Machine Translations

      7. 3.2.7Annotation of Features of English Source Texts

      8. 3.2.8Bayesian Machine Learning Classifier Relevance Vector Machine

      9. 3.2.9Training and Testing of Relevance Vector Machines with Three Different Full Feature Sets

      10. 3.2.10Classifier Optimization

      11. 3.2.11Backward Feature Elimination: RFE-SVM Method

      12. 3.2.12Separate and Joint Feature Optimization

    3. 3.3Results

    4. 3.4Comparison of Optimized RVMs with Binary Classifiers Using Readability Formula

    5. 3.5Conclusion

  6. 4Cultural and Linguistic Bias of Neural Machine Translation Technology

    1. 4.1Introduction

    2. 4.2Data Collection

    3. 4.3Development of Machine Learning Classifiers

    4. 4.4Feature Optimization

    5. 4.5Separate and Combined Feature Optimization

    6. 4.6Classifier Training and Development

    7. 4.7Statistical Refinement of the Optimized Classifier

    8. 4.8Model Stability

    9. 4.9Conclusion

  7. 5Enhancing Speech Translation in Medical Emergencies with Pictographs: BabelDr

    with contributions from Pierrette Bouillon, Johanna Gerlach, Magali Norré and Herve Spechbach

    1. 5.1Introduction

    2. 5.2Pictographs in Medical Communication

    3. 5.3BabelDr and the Bidirectional Version

    4. 5.4Usability of the Bidirectional Version of BabelDr

      1. 5.4.1Patient Satisfaction

      2. 5.4.1.1Design

    5. 5.4.1.2Results

      1. 5.4.2Pictograph Usability

        1. 5.4.2.1Design

    6. 5.4.2.2Results

      1. 5.4.2.2.1Comprehensibility of Pictographs

      2. 5.4.2.2.2Impact of the Number and Order of Pictographic Response Choices

    7. 5.5Conclusion

    8. 5.6Acknowledgments

  8. 6Healthcare Accessibility for the Deaf - The BabelDr Case Study

    with contributions from Irene Strasly, Pierrette Bouillon, Bastien David and Herve Spechbach

    1. 6.1Introduction

    2. 6.2Legal Framework in Switzerland

      1. 6.2.1Overview of the Core Principles of the Right to Health

    3. 6.3Sign Language Translation Tools for Hospitals

    4. 6.4BabelDr for Swiss-French Sign Language

      1. 6.4.1Recording Translations with Deaf Experts

      2. 6.4.2Virtual Avatar Generation

      3. 6.4.3Speech2sign Version of BabelDr

    5. 6.5Qualitative Evaluation on the Perception of Avatars and Human Videos

    6. 6.6Conclusions and Future Work

    7. 6.7Acknowledgments

  9. 7Health Websites for All: A Localisation-Oriented Accessibility Evaluation

    With contributions from Lucía Morado Vázquez and Silvia Rodríguez Vázquez

    1. 7.1Introduction

    2. 7.2Related Work

      1. 7.2.1Accessibility of Health Websites

      2. 7.2.2Localization of Health Websites

      3. 7.2.3Multilingual Web Accessibility Studies

    3. 7.3Methodology

      1. 7.3.1Data Selection

      2. 7.3.2Testing Methods

      3. 7.3.3Accessibility Features Studied

        1. 7.3.3.1Language of the Page

        2. 7.3.3.2Title of the Page

    4. 7.4Results

      1. 7.4.1Language of the Page

      2. 7.4.2Title of the Page

    5. 7.5Discussion and Conclusions

      1. 7.5.1Challenges in Localization-Oriented Accessibility Evaluation

        1. 7.5.1.1Automated Audits

        2. 7.5.1.2Definition of Compliance Criteria

        3. 7.5.1.3Need for Accessibility Enablers with an Interdisciplinary Background

      2. 7.5.2Limitations and Future Work

    6. 7.6Acknowledgments

  10. Index

Save book to Kindle

To save this book to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Available formats
×

Save book to Dropbox

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Dropbox.

Available formats
×

Save book to Google Drive

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Google Drive.

Available formats
×