Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors

TL;DR

This paper introduces a unified representation for classifying sub-level temporal relations of event time anchors, improving accuracy over previous models and addressing data scarcity with a larger annotated corpus.

Contribution

It proposes a novel quadruple-based unified representation for complex temporal relations and a multi-label classifier, outperforming existing decision tree models.

Findings

Outperforms state-of-the-art decision tree models

Larger corpus improves classification performance

Unified representation simplifies temporal relation modeling

Abstract

Extracting event time from news articles is a challenging but attractive task. In contrast to the most existing pair-wised temporal link annotation, Reimers et al.(2016) proposed to annotate the time anchor (a.k.a. the exact time) of each event. Their work represents time anchors with discrete representations of Single-Day/Multi-Day and Certain/Uncertain. This increases the complexity of modeling the temporal relations between two time anchors, which cannot be categorized into the relations of Allen's interval algebra (Allen, 1990). In this paper, we propose an effective method to decompose such complex temporal relations into sub-level relations by introducing a unified quadruple representation for both Single-Day/Multi-Day and Certain/Uncertain time anchors. The temporal relation classifiers are trained in a multi-label classification manner. The system structure of our approach is much simpler than the existing decision tree model (Reimers et al., 2018), which is composed by a dozen of node classifiers. Another contribution of this work is to construct a larger event time corpus (256 news documents) with a reasonable Inter-Annotator Agreement (IAA), for the purpose of overcoming the data shortage of the existing event time corpus (36 news documents). The empirical results show our approach outperforms the state-of-the-art decision tree model and the increase of data size obtained a significant improvement of performance.