mlsanityData to 14 Oct 2026

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness

arXiv 2410.18393 ↗First posted 24 Oct 2024cs.CL cs.SIcited by 7

Not on the map. Why?

Abstract (arXiv)

Social media is often the first place where communities discuss the latest societal trends. Prior works have utilized this platform to extract epidemic-related information (e.g. infections, preventive measures) to provide early warnings for epidemic prediction. However, these works only focused on English posts, while epidemics can occur anywhere in the world, and early discussions are often in the local, non-English languages. In this work, we introduce the first multilingual Event Extraction (EE) framework SPEED++ for extracting epidemic event information for a wide range of diseases and languages. To this end, we extend a previous epidemic ontology with 20 argument roles; and curate our multilingual EE dataset SPEED++ comprising 5.1K tweets in four languages for four diseases. Annotating data in every language is infeasible; thus we develop zero-shot cross-lingual cross-disease models (i.e., training only on English COVID data) utilizing multilingual pre-training and show their efficacy in extracting epidemic-related events for 65 diverse languages across different diseases. Experiments demonstrate that our framework can provide epidemic warnings for COVID-19 in its earliest stages in Dec 2019 (3 weeks before global discussions) from Chinese Weibo posts without any training in Chinese. Furthermore, we exploit our framework's argument extraction capabilities to aggregate community epidemic discussions like symptoms and cure measures, aiding misinformation detection and public attention monitoring. Overall, we lay a strong foundation for multilingual epidemic preparedness.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

30 of 63 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  7. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 262
  8. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  9. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 155
  10. 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 104
  11. 2021DEGREE: A Data-Efficient Generation-Based Event Extraction Modelcited by 83
  12. 2020Cross-media Structured Common Space for Multimedia Event Extractioncited by 61
18 more
  1. 2019Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detectioncited by 54
  2. 2022Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extractioncited by 40
  3. 2023TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extractioncited by 28
  4. 2022GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Rolescited by 26
  5. 2023AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Modelcited by 19
  6. 2022MEE: A Novel Multilingual Event Extraction Datasetcited by 17
  7. 2018Code-switched Language Models Using Dual RNNs and Same-Source Pretrainingcited by 16
  8. 2022TAGPRIME: A Unified Framework for Relational Structure Extractioncited by 15
  9. 2022Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatmentscited by 14
  10. 2020Weibo-COV: A Large-Scale COVID-19 Social Media Dataset from Weibocited by 11
  11. 2021Discourse-level Relation Extraction via Graph Poolingcited by 9
  12. 2020Extracting a Knowledge Base of COVID-19 Events from Social Mediacited by 7
  13. 2024Improving Event Definition Following For Zero-Shot Event Detectioncited by 7
  14. 2024Event Detection from Social Media for Epidemic Predictioncited by 7
  15. 2017Dual Language Models for Code Switched Speech Recognitioncited by 5
  16. 2021ExcavatorCovid: Extracting Events and Relations from Text Corpora for Temporal and Causal Analysis for COVID-19cited by 5
  17. 2024QUDSELECT: Selective Decoding for Questions Under Discussion Parsingcited by 5
  18. 2024GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labelingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025Instruction-Tuning LLMs for Event Extraction with Annotation Guidelinescited by 18
  2. 2025Event Extraction in Large Language Modelcited by 5
  3. 2024Dynamic Strategy Planning for Efficient Question Answering with Large Language Modelscited by 3
  4. 2025SNaRe: Domain-aware Data Generation for Low-Resource Event Detectioncited by 3
  5. 2025Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMscited by 1
  6. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
  7. 2026Calibrated Typed Decisions for Entity, Relation, and Event Extractioncited by 0