Tatiana Korelsky
$98,899
George Mason University
Virginia
Computer and Information Science and Engineering (CISE)
The advent of digital era has made natural language processing (NLP) technology both promising and important for disaster response. Language technologies can, for instance, be used for triaging the need for immediate assistance based on text messages, translating vast amounts of data related to ongoing pandemics, or engage in conversations to guide natural disaster victims. However, these advances are only limited to a few dozen of the more than 6500 languages spoken or signed in the world today, neglecting millions of people and widening the "digital divide", effectively reducing the technologies' real-world utility. This CISE Computing Research Infrastructure (CCRI) planning grant will lay out a concrete path to language technologies for crisis/disaster response that will be useful for everyone. This requires developing crucial infrastructure to support research towards technological solutions that enable and support communications in crisis scenarios. Specifically, the project will produce a thorough survey of language technologies for crisis response, in order to identify stakeholders and literature gaps. The team will then curate plans for research instrastructure, which will consist of datasets applicable to carefully curated crisis/disaster scenarios tied to prototypical language scenarios that are necessary for communicating with vulnerable populations. The planning phase will disseminate the results via a workshop, which will bring together researchers focusing on NLP, experts in disaster relief, linguistics, and human-computer interaction, as well as representatives from local speech communities, to facilitate a research community focused on language technologies for crisis response with representation from all stakeholders. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.