# Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?

Source: [Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?](<https://www.sota2.com/research/paper/68fa6f8d1e209131cea462f4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:22:26.639Z

Authors: Yuxin He, Jingyue Hu, Buzhou Tang

Published: 2023-06-01T09:53:53.000Z

## Abstract

Event co-occurrences have been proved effective for event extraction (EE) in previous studies, but have not been considered for event argument extraction (EAE) recently. In this paper, we try to fill this gap between EE research and EAE research, by highlighting the question that \`\`Can EAE models learn better when being aware of event co-occurrences?''. To answer this question, we reformulate EAE as a problem of table generation and extend a SOTA prompt-based EAE model into a non-autoregressive generation framework, called TabEAE, which is able to extract the arguments of multiple events in parallel. Under this framework, we experiment with 3 different training-inference schemes on 4 datasets (ACE05, RAMS, WikiEvents and MLEE) and discover that via training the model to extract all events in parallel, it can better distinguish the semantic boundary of each event and its ability to extract single event gets substantially improved. Experimental results show that our method achieves new state-of-the-art performance on the 4 datasets. Our code is avilable at https://github.com/Stardust-hyx/TabEAE.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Event Argument Extraction on ACE05 (test)](<https://www.sota2.com/research/sota/event-argument-extraction-on-ace05-test.md>): Event Argument Extraction; ACE05 (test); Arg-I: 75.9.

- [Event Argument Extraction on WikiEvents RAMS2Wiki](<https://www.sota2.com/research/sota/event-argument-extraction-on-wikievents-rams2wiki.md>): Event Argument Extraction; WikiEvents RAMS2Wiki; Overall F1: 26.74.

- [Event Argument Extraction on WikiEvents Wiki2Wiki](<https://www.sota2.com/research/sota/event-argument-extraction-on-wikievents-wiki2wiki.md>): Event Argument Extraction; WikiEvents Wiki2Wiki; Overall F1: 30.97.

- [Event Argument Extraction on RAMS RAMS2RAMS](<https://www.sota2.com/research/sota/event-argument-extraction-on-rams-rams2rams.md>): Event Argument Extraction; RAMS RAMS2RAMS; Overall F1: 36.22.

- [Event Argument Extraction on MLEE (test)](<https://www.sota2.com/research/sota/event-argument-extraction-on-mlee-test.md>): Event Argument Extraction; MLEE (test); Arg-I Score: 71.9.

- [Event Argument Extraction on WikiEvents (test)](<https://www.sota2.com/research/sota/event-argument-extraction-on-wikievents-test.md>): Event Argument Extraction; WikiEvents (test); Arg-C: 65.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.00502>)

[PDF](<https://arxiv.org/pdf/2306.00502.pdf>)