@inproceedings{lamba-etal-2024-humvi,
    title = "{H}um{VI}: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid",
    author = "Lamba, Hemank  and
      Abilov, Anton  and
      Zhang, Ke  and
      Olson, Elizabeth M  and
      Dambanemuya, Henry Kudzanai  and
      B{\'a}rcia, Jo{\~a}o Cordovil  and
      Batista, David S.  and
      Wille, Christina  and
      Cahill, Aoife  and
      Tetreault, Joel R.  and
      Jaimes, Alejandro",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.743/",
    doi = "10.18653/v1/2024.findings-emnlp.743",
    pages = "12705--12722",
    abstract = "Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI {--} a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset."
}

@article{batista2013extracccao,
  title = {Extraction of Support and Opposition Relationships in Portuguese Political News Headlines},
  author = {Batista, David Soares},
  journal = {Linguam{\'a}tica},
  volume = {15},
  number = {1},
  year = {2023}
}

@incollection{kovens2019
  title = {COMTRAVO-DS team at GermEval 2019 Task 1 on Hierarchical Classification of Blurbs},
  author = {Batista, David S and Lyra, Matti},
  school = {KONVENS, 2019, Erlangen, Germany},
  year = {2019}
}

@incollection{phd-dsbatista2016
  title = {Large-Scale Semantic Relationship Extraction for Information Discovery},
    author = {Batista, David S.},
  school = {Instituto Superior Técnico, Universidade de Lisboa},
  year = {2016}
}

@incollection{batista2015emnlp,
  title = {Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics},
  author = {Batista, David S and Martins, Bruno and Silva, M{\'a}rio J},
  booktitle = {In Empirical Methods in Natural Language Processing},
  year = {2015},
  publisher = {ACL}
}

@incollection{batista2013minwise,
  title = {A Minwise Hashing Method for Addressing Relationship Extraction from Text},
  author = {Batista, David S and Silva, Rui and Martins, Bruno and Silva, M{\'a}rio J},
  booktitle = {Web Information Systems Engineering--WISE 2013},
  year = {2013},
  publisher = {Springer Berlin Heidelberg}
}

@incollection{santos2013document,
  title = {Document Analytics through Entity Resolution},
  author = {Santos, Jo{\~a}o and Martins, Bruno and Batista, David S},
  booktitle = {Web Information Systems Engineering--WISE 2013},
  year = {2013},
  publisher = {Springer Berlin Heidelberg}
}

@article{batista2013extracccao,
  title = {Exploring DBpedia and Wikipedia for Portuguese Semantic Relationship Extraction},
  author = {Batista, David Soares and Forte, David and Silva, Rui and Martins, Bruno and Silva, M{\'a}rio J.},
  journal = {Linguam{\'a}tica},
  volume = {5},
  number = {1},
  year = {2013}
}

@article{moreira2013tracking,
  title = {Tracking politics with POWER},
  author = {Moreira, Silvio and Batista, David S and Carvalho, Paula and Couto, Francisco M and Silva, Mario J},
  journal = {Program: electronic library and information systems},
  volume = {47},
  number = {2},
  year = {2013},
  publisher = {Emerald Group Publishing Limited}
}

@incollection{batista2012toponym,
  title = {Toponym Disambiguation using Ontology-based Semantic Similarity},
  author = {Batista, David S and Ferreira, Jo{\~a}o D and Couto, Francisco M and Silva, M{\'a}rio J},
  booktitle = {Computational Processing of the Portuguese Language},
  year = {2012},
  publisher = {Springer Berlin Heidelberg}
}

@incollection{moreira2011power,
  title = {POWER - Politics Ontology for Web Entity Retrieval},
  author = {Moreira, Silvio and Batista, David and Carvalho, Paula and Couto, Francisco M and Silva, M{\'a}rio J},
  booktitle = {Advanced Information Systems Engineering Workshops},
  year = {2011},
  publisher = {Springer Berlin Heidelberg}
}

@inproceedings{batista2010statistical,
  title = {A Statistical Study of the WPT05 Crawl of the Portuguese Web},
  author = {Batista, David and Silva, M{\'a}rio J},
  booktitle = {FALA 2010 VI Jornadas en Tecnolog{\'\i}a del Habla and II Iberian SLTech Workshop, Vigo, Spain},
  year = {2010},
  publisher = {Universidade de Vigo}
}

@techreport{ferreira2010geo</a>,
  title = {The Geo-Net-PT/Yahoo! GeoPlanet (TM) concordance},
  author = {Ferreira, Joao D and Batista, David S and Couto, Francisco M and Silva, M{\'a}rio J},
  year = {2010},
  institution = {Universidade de Lisboa},
  doi = {10451/14174}
}

@inproceedings{batista2010geographic,
  title = {Geographic Signatures for Semantic Retrieval},
  author = {Batista, David S and Silva, M{\'a}rio J and Couto, Francisco M and Behera, Bibek},
  booktitle = {Proceedings of the 6th Workshop on Geographic Information Retrieval},
  year = {2010},
  publisher = {ACM}
}

@incollection{cardoso2010wikipedia,
  title = {Where in the Wikipedia is that answer? The XLDB at the GikiCLEF 2009 task},
  author = {Cardoso, Nuno and Batista, David and Lopez-Pellicer, Francisco J and Silva, M{\'a}rio J},
  booktitle = {Multilingual Information Access Evaluation I. Text Retrieval Experiments},
  year = {2010},
  publisher = {Springer Berlin Heidelberg}
}

@mastersthesis{dsbatista2009:msc-thesis,
  author = {Batista, David Soares},
  title = {Prospec{\c{c}}{\~a}o de Conceitos Geogr{\'a}ficos na Web},
  school = {Universidade de Lisboa},
  year = {2009},
  doi = {10451/4510}
}