Conflibert: A pre-trained language model for political conflict and violence

Y Hu, MS Hosseini, E Skorupa Parolin, J Osorio… - 2022 - par.nsf.gov
Analyzing conflicts and political violence around the world is a persistent challenge in the
political science and policy communities due in large part to the vast volumes of specialized …

Bert has more to offer: Bert layers combination yields better sentence embeddings

MS Hosseini, M Munia, L Khan - Findings of the Association for …, 2023 - aclanthology.org
Obtaining sentence representations from BERT-based models as feature extractors is
invaluable as it takes much less time to pre-compute a one-time representation of the data …

Controllable fake document infilling for cyber deception

Y Hu, Y Lin, ES Parolin, L Khan, K Hamlen - arXiv preprint arXiv …, 2022 - arxiv.org
Recent works in cyber deception study how to deter malicious intrusion by generating
multiple fake versions of a critical document to impose costs on adversaries who need to …

Conflibert-spanish: A pre-trained spanish language model for political conflict and violence

W Yang, S Alsarra, L Abdeljaber… - 2023 7th IEEE …, 2023 - ieeexplore.ieee.org
This article introduces ConfliBERT-Spanish, a pre-trained language model specialized in
political conflict and violence for text written in the Spanish language. Our methodology …

Confli-t5: An autoprompt pipeline for conflict related text augmentation

ES Parolin, Y Hu, L Khan, PT Brandt… - … Conference on Big …, 2022 - ieeexplore.ieee.org
Recent advances in natural language processing (NLP) and Big Data technologies have
been crucial for scientists to analyze political unrest and violence, prevent harm, and …

Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification

Y Hu, ES Parolin, L Khan, P Brandt… - Proceedings of the …, 2024 - aclanthology.org
Is it possible accurately classify political relations within evolving event ontologies without
extensive annotations? This study investigates zero-shot learning methods that use expert …

Synthesizing Political Zero-Shot Relation Classification via Codebook Knowledge, NLI, and ChatGPT

Y Hu, ES Parolin, L Khan, PT Brandt, J Osorio… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent supervised models for event coding vastly outperform pattern-matching methods.
However, their reliance solely on new annotations disregards the vast knowledge within …

Rethinking the event coding pipeline with prompt entailment

C Lefebvre, N Stoehr - arXiv preprint arXiv:2210.05257, 2022 - arxiv.org
For monitoring crises, political events are extracted from the news. The large amount of
unstructured full-text event descriptions makes a case-by-case analysis unmanageable …

Deep Active Learning for Data Mining from Conflict Text Corpora

M Croicu - arXiv preprint arXiv:2402.01577, 2024 - arxiv.org
High-resolution event data on armed conflict and related processes have revolutionized the
study of political contention with datasets like UCDP GED, ACLED etc. However, most of …

Transfer Learning and Uncertainty Quantification in Natural Language Processing for Political Science and Cyber Security

Y Hu - 2023 - search.proquest.com
Abstract Recent advancements in Natural Language Processing (NLP) driven by pretrained
language models have revolutionized various fields reliant on large-scale text-based …