Saved in:
Bibliographic Details
Main Authors: Zhang, Xinliang Frederick, Blum, Carter, Choji, Temma, Shah, Shalin, Vempala, Alakananda
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917962329358336
author Zhang, Xinliang Frederick
Blum, Carter
Choji, Temma
Shah, Shalin
Vempala, Alakananda
author_facet Zhang, Xinliang Frederick
Blum, Carter
Choji, Temma
Shah, Shalin
Vempala, Alakananda
contents Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of identifying role-specific text spans (i.e., arguments) for a given event. Document-level EAE (DocEAE) focuses on arguments that are scattered across an entire document. In this work, we explore open-source Large Language Models (LLMs) for DocEAE, and propose ULTRA, a hierarchical framework that extracts event arguments more cost-effectively. Further, it alleviates the positional bias issue intrinsic to LLMs. ULTRA sequentially reads text chunks of a document to generate a candidate argument set, upon which non-pertinent candidates are dropped through self-refinement. We introduce LEAFER to address the challenge LLMs face in locating the exact boundary of an argument. ULTRA outperforms strong baselines, including strong supervised models and ChatGPT, by 9.8% when evaluated by Exact Match (EM).
format Preprint
id arxiv_https___arxiv_org_abs_2401_13218
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement
Zhang, Xinliang Frederick
Blum, Carter
Choji, Temma
Shah, Shalin
Vempala, Alakananda
Computation and Language
Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of identifying role-specific text spans (i.e., arguments) for a given event. Document-level EAE (DocEAE) focuses on arguments that are scattered across an entire document. In this work, we explore open-source Large Language Models (LLMs) for DocEAE, and propose ULTRA, a hierarchical framework that extracts event arguments more cost-effectively. Further, it alleviates the positional bias issue intrinsic to LLMs. ULTRA sequentially reads text chunks of a document to generate a candidate argument set, upon which non-pertinent candidates are dropped through self-refinement. We introduce LEAFER to address the challenge LLMs face in locating the exact boundary of an argument. ULTRA outperforms strong baselines, including strong supervised models and ChatGPT, by 9.8% when evaluated by Exact Match (EM).
title ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement
topic Computation and Language
url https://arxiv.org/abs/2401.13218