Linear Cross-document Event Coreference Resolution with X-AMR

Shafiuddin Rehan Ahmed, George Arthur Baker, Evi Judge, Michael Reagan, Kristin Wright-Bettner, Martha Palmer, James H. Martin


Abstract
Event Coreference Resolution (ECR) as a pairwise mention classification task is expensive both for automated systems and manual annotations. The task’s quadratic difficulty is exacerbated when using Large Language Models (LLMs), making prompt engineering for ECR prohibitively costly. In this work, we propose a graphical representation of events, X-AMR, anchored around individual mentions using a cross-document version of Abstract Meaning Representation. We then linearize the ECR with a novel multi-hop coreference algorithm over the event graphs. The event graphs simplify ECR, making it a) LLM cost-effective, b) compositional and interpretable, and c) easily annotated. For a fair assessment, we first enrich an existing ECR benchmark dataset with these event graphs using an annotator-friendly tool we introduce. Then, we employ GPT-4, the newest LLM by OpenAI, for these annotations. Finally, using the ECR algorithm, we assess GPT-4 against humans and analyze its limitations. Through this research, we aim to advance the state-of-the-art for efficient ECR and shed light on the potential shortcomings of current LLMs at this task. Code and annotations: https://github.com/ahmeshaf/gpt_coref
Anthology ID:
2024.lrec-main.920
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:
10517–10529
Language:
URL:
https://aclanthology.org/2024.lrec-main.920
DOI:
Bibkey:
Cite (ACL):
Shafiuddin Rehan Ahmed, George Arthur Baker, Evi Judge, Michael Reagan, Kristin Wright-Bettner, Martha Palmer, and James H. Martin. 2024. Linear Cross-document Event Coreference Resolution with X-AMR. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10517–10529, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Linear Cross-document Event Coreference Resolution with X-AMR (Ahmed et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.920.pdf