Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction
This work addresses event argument extraction for natural language processing applications, representing an incremental improvement by refining prompt-tuning techniques with entity and role information.
The authors tackled the problem of event argument extraction by proposing a bi-directional iterative prompt-tuning method that incorporates entity information and argument role interactions, achieving state-of-the-art performance on the ACE 2005 English dataset in both standard and low-resource settings.
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.