Graph-Based Decoding for Event Sequencing and Coreference Resolution

TL;DR

This paper introduces a graph-based decoding algorithm for event coreference and sequencing, outperforming existing methods and enabling flexible feature use, with state-of-the-art results on TAC-KBP 2015.

Contribution

It proposes a novel graph-based decoding approach suitable for both event coreference and sequencing, addressing limitations of tree-like structures.

Findings

Achieved state-of-the-art performance on TAC-KBP 2015 event coreference task.

Outperformed a strong temporal-based baseline in event sequencing.

Demonstrated the flexibility of the new decoding algorithm for different event relations.

Abstract

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.