Extracting Temporal Event Relation with Syntax-guided Graph Transformer

TL;DR

This paper introduces a Syntax-guided Graph Transformer (SGT) that improves extraction of temporal relations between events in text by leveraging dependency parsing and syntax-guided attention, outperforming previous methods on benchmark datasets.

Contribution

The paper presents a novel SGT model that explicitly uses dependency trees and a syntax-guided attention mechanism to better capture temporal relations in text.

Findings

Significantly outperforms previous state-of-the-art methods on MATRES and TB-Dense datasets.

Demonstrates robustness on the contrast set of MATRES.

Code is publicly available for reproducibility.

Abstract

Extracting temporal relations (e.g., before, after, and simultaneous) among events is crucial to natural language understanding. One of the key challenges of this problem is that when the events of interest are far away in text, the context in-between often becomes complicated, making it challenging to resolve the temporal relationship between them. This paper thus proposes a new Syntax-guided Graph Transformer network (SGT) to mitigate this issue, by (1) explicitly exploiting the connection between two events based on their dependency parsing trees, and (2) automatically locating temporal cues between two events via a novel syntax-guided attention mechanism. Experiments on two benchmark datasets, MATRES and TB-Dense, show that our approach significantly outperforms previous state-of-the-art methods on both end-to-end temporal relation extraction and temporal relation classification; This improvement also proves to be robust on the contrast set of MATRES. The code is publicly available at https://github.com/VT-NLP/Syntax-Guided-Graph-Transformer.