Graph-Based Decoding for Event Sequencing and Coreference Resolution
This addresses the challenge of interrelated events in text for natural language processing applications, representing an incremental improvement with a unified method for two tasks.
The paper tackled the problem of modeling event coreference and sequencing in text by proposing a graph-based decoding algorithm, achieving state-of-the-art performance on the TAC-KBP 2015 event coreference task and outperforming a strong baseline for event sequencing.
Events in text documents are interrelated in complex ways. In this paper, we study two types of relation: Event Coreference and Event Sequencing. We show that the popular tree-like decoding structure for automated Event Coreference is not suitable for Event Sequencing. To this end, we propose a graph-based decoding algorithm that is applicable to both tasks. The new decoding algorithm supports flexible feature sets for both tasks. Empirically, our event coreference system has achieved state-of-the-art performance on the TAC-KBP 2015 event coreference task and our event sequencing system beats a strong temporal-based, oracle-informed baseline. We discuss the challenges of studying these event relations.