Language Technology to Improve Data Quality and Engagement
By Translators Without Borders US
Needs assessments are often inaccurate and slow in multilingual contexts, a poor basis for humanitarian strategies. Data collectors often do not speak the languages of conflict-affected people, do not understand humanitarian terminology and have limited training. This means that important information may be translated several times, making the process slow and prone to error, resulting in aid efforts designed on incomplete and inaccurate data. The voices, needs, and concerns of conflict affected populations, including internally-displaced persons, go unheard, lost in layers of translation.
Translators Without Borders will build cutting edge language technology in marginalized languages – in text and voice based systems – to better capture, understand, and analyze information in a quick and accurate way. This will allow humanitarian aid workers to more accurately capture the needs of the hardest to reach.
To do assessments, field workers act as surveyors, translators, interpreters, and recorders, collecting information in local languages and translating to English for analysis. This project will test a process to capture and analyze multilingual audio survey data collected during quantitative and qualitative assessments in hard-to-reach areas in Nigeria. Near real-time analysis of unstructured audio data will be possible, reducing the analysis and decision-making process to a matter of days, instead of weeks. This will ensure accurate translation and reliable data, resulting in better informed humanitarian programming and donor agendas, more responsive to the needs of affected people.