Asking and Answering Questions to Extract Event-Argument Structures
Md Nayem Uddin, Enfa Rose George, Eduardo Blanco, Steven R. Corman
Abstract
This paper presents a question-answering approach to extract document-level event-argument structures. We automatically ask and answer questions for each argument type an event may have. Questions are generated using manually defined templates and generative transformers. Template-based questions are generated using predefined role-specific wh-words and event triggers from the context document. Transformer-based questions are generated using large language models trained to formulate questions based on a passage and the expected answer. Additionally, we develop novel data augmentation strategies specialized in inter-sentential event-argument relations. We use a simple span-swapping technique, coreference resolution, and large language models to augment the training instances. Our approach enables transfer learning without any corpora-specific modifications and yields competitive results with the RAMS dataset. It outperforms previous work, and it is especially beneficial to extract arguments that appear in different sentences than the event trigger. We also present detailed quantitative and qualitative analyses shedding light on the most common errors made by our best model.- Anthology ID:
- 2024.lrec-main.142
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 1609–1626
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.142
- DOI:
- Cite (ACL):
- Md Nayem Uddin, Enfa Rose George, Eduardo Blanco, and Steven R. Corman. 2024. Asking and Answering Questions to Extract Event-Argument Structures. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1609–1626, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Asking and Answering Questions to Extract Event-Argument Structures (Uddin et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.142.pdf