Summary of Humvi: a Multilingual Dataset For Detecting Violent Incidents Impacting Humanitarian Aid, by Hemank Lamba et al.
HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid
by Hemank Lamba, Anton Abilov, Ke Zhang, Elizabeth M. Olson, Henry k. Dambanemuya, João c. Bárcia, David S. Batista, Christina Wille, Aoife Cahill, Joel Tetreault, Alex Jaimes
First submitted to arxiv on: 8 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to analyzing violent incidents and enhancing humanitarian operations is proposed in this paper. The authors present HumVI, a dataset of news articles in English, French, and Arabic, categorized by the humanitarian sector they impact. This dataset was created with the help of Insecurity Insight, a data-backed humanitarian organization. To address different task-related challenges, various deep learning architectures and techniques were employed, including data augmentation and mask loss. The authors provide multiple benchmarks for the dataset, demonstrating its effectiveness in classifying violent incidents. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Humanitarian organizations can make better decisions by understanding trends and patterns in violent incidents that affect their work. However, this information is often hard to find. A new way of collecting and organizing data about these incidents has been developed. This project created a large dataset of news articles in three languages that are labeled according to the type of violence and the humanitarian sector it affects. The goal is to help organizations make better decisions and improve their work. |
Keywords
» Artificial intelligence » Data augmentation » Deep learning » Mask
