Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929387049320448 |
|---|---|
| author | Liu, Wanlong Zhou, Li Zeng, Dingyi Xiao, Yichen Cheng, Shaohuan Zhang, Chen Lee, Grandee Zhang, Malu Chen, Wenyu |
| author_facet | Liu, Wanlong Zhou, Li Zeng, Dingyi Xiao, Yichen Cheng, Shaohuan Zhang, Chen Lee, Grandee Zhang, Malu Chen, Wenyu |
| contents | Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events. To address these limitations, here we propose a multiple-event argument extraction model DEEIA (Dependency-guided Encoding and Event-specific Information Aggregation), capable of extracting arguments from all events within a document simultaneouslyThe proposed DEEIA model employs a multi-event prompt mechanism, comprising DE and EIA modules. The DE module is designed to improve the correlation between prompts and their corresponding event contexts, whereas the EIA module provides event-specific information to improve contextual understanding. Extensive experiments show that our method achieves new state-of-the-art performance on four public datasets (RAMS, WikiEvents, MLEE, and ACE05), while significantly saving the inference time compared to the baselines. Further analyses demonstrate the effectiveness of the proposed modules. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01884 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction Liu, Wanlong Zhou, Li Zeng, Dingyi Xiao, Yichen Cheng, Shaohuan Zhang, Chen Lee, Grandee Zhang, Malu Chen, Wenyu Computation and Language Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events. To address these limitations, here we propose a multiple-event argument extraction model DEEIA (Dependency-guided Encoding and Event-specific Information Aggregation), capable of extracting arguments from all events within a document simultaneouslyThe proposed DEEIA model employs a multi-event prompt mechanism, comprising DE and EIA modules. The DE module is designed to improve the correlation between prompts and their corresponding event contexts, whereas the EIA module provides event-specific information to improve contextual understanding. Extensive experiments show that our method achieves new state-of-the-art performance on four public datasets (RAMS, WikiEvents, MLEE, and ACE05), while significantly saving the inference time compared to the baselines. Further analyses demonstrate the effectiveness of the proposed modules. |
| title | Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.01884 |