Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction

10/28/2022
by   Lu Dai, et al.
0

Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE). However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information. In this paper, we propose a bi-directional iterative prompt-tuning method for EAE, where the EAE task is treated as a cloze-style task to take full advantage of entity information and pre-trained language models (PLMs). Furthermore, our method explores event argument interactions by introducing the argument roles of contextual entities into prompt construction. Since template and verbalizer are two crucial components in a cloze-style prompt, we propose to utilize the role label semantic knowledge to construct a semantic verbalizer and design three kinds of templates for the EAE task. Experiments on the ACE 2005 English dataset with standard and low-resource settings show that the proposed method significantly outperforms the peer state-of-the-art methods. Our code is available at https://github.com/HustMinsLab/BIP.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/01/2021

Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder

Capturing interactions among event arguments is an essential step toward...
research
11/03/2022

Open-Vocabulary Argument Role Prediction for Event Extraction

The argument role in event extraction refers to the relation between an ...
research
12/01/2018

One for All: Neural Joint Modeling of Entities and Events

The previous work for event extraction has mainly focused on the predict...
research
02/24/2022

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

In this paper, we propose an effective yet efficient model PAIE for both...
research
10/01/2021

Learning to Ask for Data-Efficient Event Argument Extraction

Event argument extraction (EAE) is an important task for information ext...
research
10/18/2022

EventGraph at CASE 2021 Task 1: A General Graph-based Approach to Protest Event Extraction

This paper presents our submission to the 2022 edition of the CASE 2021 ...
research
11/14/2022

Retrieval-Augmented Generative Question Answering for Event Argument Extraction

Event argument extraction has long been studied as a sequential predicti...

Please sign up or login with your details

Forgot password? Click here to reset