MM4MT

Purpose of the Study

This research is being conducted by Marine Carpuat at the University of Maryland, College Park. The purpose of this research project is to measure and calibrate user's mental models of machine translation. The research investigates ways to design safe and reliable machine translation technology by studying how people perceive and act upon possibly imperfect machine translations.

Procedures

You will participate in tasks designed to see how users make sense of the strengths and weaknesses of MT systems. You will be presented with machine translations generated by AI systems, which may include AI-generated assessments of the translation quality. You will be asked to answer multiple-choice questions or provide short text inputs based on your understanding on these machine translations and AI assessments. All sessions will take place online either via a Qualtrics-style survey platform or a dedicated web application. Each session will take no longer than 60 minutes. The study does not collect demographic information such as age or gender. It collects minimal information, such as your first language, language proficiency in English and {target language}, and use of AI translation tools (e.g., Google Translate) in your daily work and life. You are required to answer these questions.

Potential Risks

There are no known risks associated with participants of this study.

Potential Benefits

The studies are being conducted solely for research purposes, and are not expected to directly benefit participants. Participants may indirectly benefit from participating in the study by gaining knowledge about the capabilities of AI systems. In the long term, the findings may benefit a broader population by improving AI translation technology.

Confidentiality

Crowdworker ID is the only potentially identifying information, which will be removed from the data after the participants are paid. Only the principal investigator and the co-investigators of the study will have access to the data before they are removed.

All data will be anonymized prior to public release and responses cannot be linked to individuals.

Any potential loss of confidentiality will be minimized by storing data in a secured internal platform at University of Maryland, College Park.

Your information may be shared with representatives of the University of Maryland, College Park or governmental authorities if you or someone else is in danger or if we are required to do so by law.

Compensation

We will pay recruited participants a fair, hourly wage (at a minimum $15/hour MD minimum wage). If your accuracy exceeds 80%, you will receive a performance-based bonus of 25% of base compensation.

Right to Withdraw and Questions

Participation in the study is completely voluntary. If you decide to participate in this research, you may stop participating at any time. If you have questions, concerns, or complaints, or if you need to report an injury related to the research, please contact the investigator:

Marine Carpuat
Iribe 4130 University of Maryland
College Park, Maryland, 20742
E-mail: marine@umd.edu

Participant Rights

If you have questions about your rights as a research participant or wish to report a research-related injury, please contact:

University of Maryland College Park
Institutional Review Board Office
1204 Marie Mount Hall
College Park, Maryland, 20742
E-mail: irb@umd.edu
Telephone: 301-405-0678

For more information regarding participant rights, please visit:
Participant Rights Information

This research has been reviewed according to the University of Maryland, College Park IRB procedures for research involving human subjects.

Statement of Consent

Statement of Consent By clicking 'I consent to participate in the study', you indicate that you are at least 18 years of age; you have read this consent information or have had it read to you; your questions have been answered to your satisfaction and you voluntarily agree to participate in this research study. Please download/print/save a copy of this consent information for your records.

Today's Date:

Approved as IRBNet Package: 2245213-3