Take Shelter, Zanmi: Digitally Alerting Cyclone Victims in Their Languages

Domain:

natural language processing

Record type:

paper

Creator:

AssRom

Publisher:

Und

Host:

Natural disasters such as tropical cyclones cause annual devastation and take a heavy so- cial cost, as disadvantaged communities are typ- ically hit hardest. Among these communities are the speakers of minority and low-resource languages, who may not be sufficiently in- formed about incoming weather events to pre- pare. This work presents an analysis of the current state of machine translation for natural disasters in the languages of communities that are threatened by them. Results suggest that commercial systems are promising, and that in-genre fine-tuning data are beneficial.

Visit

doi.org underline.io

Tasks

machine translation

Emergency Alerting and Evidence Collection System

Emergency Alerting and Evidence Collection System Abstract Personal safety during physical assau

State patients charged with parricide: a thematic analysis of their relationship experiences with their victims

The mentally ill offender is considered to be an independent category when discussing the typology o

Inclusive shelter provision in Mogadishu

This article is based on a research project led by the International Institute for Environment and D

Representing pulaar digitally

NIYIBIZIJoseph/quarry-digitally

HENG YUN Quarry ERP System - A comprehensive enterprise resource planning platform for quarry and sa

Trains of African Easterly Waves and Their Relationship to Tropical Cyclone Genesis in the Eastern Atlantic

International audience In this study, the relationship between trains of African east