Document-Level Event Argument Extraction via Optimal Transport
Amir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt, Bonan Min, Thien Huu Nguyen
Abstract
Event Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger. Despite the success of prior works in sentence-level EAE, the document-level setting is less explored. In particular, whereas syntactic structures of sentences have been shown to be effective for sentence-level EAE, prior document-level EAE models totally ignore syntactic structures for documents. Hence, in this work, we study the importance of syntactic structures in document-level EAE. Specifically, we propose to employ Optimal Transport (OT) to induce structures of documents based on sentencelevel syntactic structures and tailored to EAE task. Furthermore, we propose a novel regularization technique to explicitly constrain the contributions of unrelated context words in the final prediction for EAE. We perform extensive experiments on the benchmark documentlevel EAE dataset RAMS that leads to the state-of-the-art performance. Moreover, our experiments on the ACE 2005 dataset reveals the effectiveness of the proposed model in the sentence-level EAE by establishing new stateof-the-art results.