{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/linear-cross-document-event-coreference","title":"Linear Cross-document Event Coreference Resolution with X-AMR","arxiv_id":"2404.08656","date":"2024-03-25","proceeding":null,"authors":["Shafiuddin Rehan Ahmed","George Arthur Baker","Evi Judge","Michael Regan","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 \\textbf{cross}-document version of \\textbf{A}bstract \\textbf{M}eaning \\textbf{R}epresentation. 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: \\url{https://github.com/ahmeshaf/gpt_coref}","url_abs":"https://arxiv.org/abs/2404.08656v1","url_pdf":"https://arxiv.org/pdf/2404.08656v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"linear-cross-document-event-coreference","repo_url":"https://github.com/ahmeshaf/gpt_coref","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"event-coreference-resolution","task_name":"Event Coreference Resolution"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.08656","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}