Extracting Event Temporal Relations via Hyperbolic Geometry

TL;DR

This paper introduces hyperbolic space embeddings for event temporal relation extraction, capturing hierarchical and asymmetric relations more effectively than traditional Euclidean embeddings, leading to state-of-the-art results.

Contribution

It proposes two novel hyperbolic embedding methods for event relation extraction, demonstrating their superiority over Euclidean approaches in capturing complex event semantics.

Findings

Achieved state-of-the-art performance on standard datasets.

Hyperbolic embeddings better encode hierarchical event relations.

Qualitative analyses reveal rich semantic encoding in hyperbolic space.

Abstract

Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.