Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction
This work addresses event argument extraction for natural language processing applications, presenting an incremental improvement with transferable question generation strategies across corpora.
The paper tackles document-level event argument extraction by generating both uncontextualized and contextualized questions without human involvement, showing that combining these question types improves performance, particularly when event triggers and arguments are in different sentences.
This paper presents multiple question generation strategies for document-level event argument extraction. These strategies do not require human involvement and result in uncontextualized questions as well as contextualized questions grounded on the event and document of interest. Experimental results show that combining uncontextualized and contextualized questions is beneficial, especially when event triggers and arguments appear in different sentences. Our approach does not have corpus-specific components, in particular, the question generation strategies transfer across corpora. We also present a qualitative analysis of the most common errors made by our best model.