LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912408650383360 |
|---|---|
| author | Semnani, Sina J. Zhang, Pingyue Zhai, Wanyue Li, Haozhuo Beauchamp, Ryan Billing, Trey Kishi, Katayoun Li, Manling Lam, Monica S. |
| author_facet | Semnani, Sina J. Zhang, Pingyue Zhai, Wanyue Li, Haozhuo Beauchamp, Ryan Billing, Trey Kishi, Katayoun Li, Manling Lam, Monica S. |
| contents | This paper presents LEMONADE, a large-scale conflict event dataset comprising 39,786 events across 20 languages and 171 countries, with extensive coverage of region-specific entities. LEMONADE is based on a partially reannotated subset of the Armed Conflict Location & Event Data (ACLED), which has documented global conflict events for over a decade.
To address the challenge of aggregating multilingual sources for global event analysis, we introduce abstractive event extraction (AEE) and its subtask, abstractive entity linking (AEL). Unlike conventional span-based event extraction, our approach detects event arguments and entities through holistic document understanding and normalizes them across the multilingual dataset. We evaluate various large language models (LLMs) on these tasks, adapt existing zero-shot event extraction systems, and benchmark supervised models. Additionally, we introduce ZEST, a novel zero-shot retrieval-based system for AEL.
Our best zero-shot system achieves an end-to-end F1 score of 58.3%, with LLMs outperforming specialized event extraction models such as GoLLIE. For entity linking, ZEST achieves an F1 score of 45.7%, significantly surpassing OneNet, a state-of-the-art zero-shot baseline that achieves only 23.7%. However, these zero-shot results lag behind the best supervised systems by 20.1% and 37.0% in the end-to-end and AEL tasks, respectively, highlighting the need for further research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00980 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World Semnani, Sina J. Zhang, Pingyue Zhai, Wanyue Li, Haozhuo Beauchamp, Ryan Billing, Trey Kishi, Katayoun Li, Manling Lam, Monica S. Computation and Language This paper presents LEMONADE, a large-scale conflict event dataset comprising 39,786 events across 20 languages and 171 countries, with extensive coverage of region-specific entities. LEMONADE is based on a partially reannotated subset of the Armed Conflict Location & Event Data (ACLED), which has documented global conflict events for over a decade. To address the challenge of aggregating multilingual sources for global event analysis, we introduce abstractive event extraction (AEE) and its subtask, abstractive entity linking (AEL). Unlike conventional span-based event extraction, our approach detects event arguments and entities through holistic document understanding and normalizes them across the multilingual dataset. We evaluate various large language models (LLMs) on these tasks, adapt existing zero-shot event extraction systems, and benchmark supervised models. Additionally, we introduce ZEST, a novel zero-shot retrieval-based system for AEL. Our best zero-shot system achieves an end-to-end F1 score of 58.3%, with LLMs outperforming specialized event extraction models such as GoLLIE. For entity linking, ZEST achieves an F1 score of 45.7%, significantly surpassing OneNet, a state-of-the-art zero-shot baseline that achieves only 23.7%. However, these zero-shot results lag behind the best supervised systems by 20.1% and 37.0% in the end-to-end and AEL tasks, respectively, highlighting the need for further research. |
| title | LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00980 |