Language Technology for Crisis Preparedness and Response

Apr 1, 2023 5 min read

June 1-2, George Mason University, Fairfax, VA.

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 planning workshop aims to 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. Our goal is to curate plans for research infrastructure, 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.

When: June 1-2
Where: Fairfax, VA. George Mason University, Horizon Hall, Room 2010.

Registration

Please fill in the brief registration form here to help us with the workshop logistics

Tentative Program

Note: All times listed are EDT (UTC-4)

Wednesday, May 31

6pm	Kickoff Dinner for in-person participants. Location TBA

Thursday, June 1
Morning Session:

9:00am	Breakfast and Coffee
9:15am	Welcome Note, Introductions, Goals
9:30am	Invited Talk by Will Lewis, University of Washington
10:30am	Roundtable Session 1: Disaster/Crises Experiences and Scenarios
11:30am	Brief Presentations
12:00pm	Lunch Break

Afternoon Session:

1:30pm	Invited Talk by Manuel Locria, CLEAR Global / Translators without Borders
2:30pm	Coffee
3:00pm	Roundtable Session 2: Data, Scenarios, and Language Technologies
4:30pm	Brief Presentations and Wrap-up
6:00pm	Dinner (optional)

Friday, June 2
Morning Session:

9:00am	Breakfast and Coffee
9:15am	Summary of Yesterday's Work and Goals for the Day
9:30am	Invited Talk by Kalika Bali, MSR India
10:30am	Roundtable Session 3: Specifics of Research Infrastructure
11:30am	Brief Presentations and Wrap-Up
12:00pm	Lunch

Afternoon Session:

1:30 - 4:00pm	Working Groups (+Coffee)
6:00pm	Dinner (optional)

Invited Talk Information

Will Lewis: Language Technologies in Crises
Abstract: I will start with a brief background on the importance of information in crises and how communication is essential to relay such information between affected parties—nominally between aid providers and those requiring aid, but also between aid providers themselves, along with broadcasting information to the larger world. I will then jump into how language technologies have been used in crises in the past, from the use of NLP and MT in Haiti after the devastating earthquake of 2010, to the use of NLP to process social media and microblogs, to the potential of social media to broadcast mis/disinformation and what we might do to detect it, and to the limited use of speech technologies in crisis response. I will then look at the path forward, with a focus on these questions: How should we use language technologies in crises? What languages and communities should we target first? How much can we do in advance of the next crisis?

Manuel Locria: Enhancing Communication: Engaging Communities with AI-Powered Language Solutions for Conversations
Abstract: We all have a role to play as we work towards a more equitable and inclusive future, from large institutions to grass-roots organizations, from humanitarians to technologists. Yet without language equity, people are excluded from global conversations about key topics. Language resources and technologies are only available to half the world's population. Four billion people are being left behind because they can’t connect and get information in their language. We can help bridge this gap by using innovative technologies such as machine translation, speech recognition and natural language processing to build AI-powered language solutions with high social impact in marginalized languages.

Kalika Bali: Global Readiness of Language Technology for Healthcare: What would it Take to Combat the Next Pandemic?
Abstract: The COVID-19 pandemic has brought out both the best and worst of language technology (LT). On one hand, conversational agents for information dissemination and basic diagnosis have seen widespread use, and arguably, had an important role in combating the pandemic. On the other hand, it has also become clear that such technologies are readily available for a handful of languages, and the vast majority of the global south is completely bereft of these benefits. What is the state of LT, especially conversational agents, for healthcare across the world's languages? And, what would it take to ensure global readiness of LT before the next pandemic? In this paper, we try to answer these questions through survey of existing literature and resources, as well as through a rapid chatbot building exercise for 15 Asian and African languages with varying amount of resource-availability. The study confirms the pitiful state of LT even for languages with large speaker bases, such as Sinhala and Hausa, and identifies the gaps that could help us prioritize research and investment strategies in LT for healthcare.