Detecting Ongoing Events Using Contextual Word and Sentence Embeddings

TL;DR

This paper defines the Ongoing Event Detection (OED) task, introduces a new dataset, and proposes an RNN model utilizing BERT embeddings that effectively identifies ongoing events in news texts, outperforming existing models.

Contribution

It introduces the OED task with a labeled dataset and presents a novel RNN model using contextual embeddings for ongoing event detection.

Findings

The proposed model outperforms baseline models.

Contextual embeddings significantly improve detection accuracy.

Extensive experiments validate the effectiveness of the approach.

Abstract

This paper introduces the Ongoing Event Detection (OED) task, which is a specific Event Detection task where the goal is to detect ongoing event mentions only, as opposed to historical, future, hypothetical, or other forms or events that are neither fresh nor current. Any application that needs to extract structured information about ongoing events from unstructured texts can take advantage of an OED system. The main contribution of this paper are the following: (1) it introduces the OED task along with a dataset manually labeled for the task; (2) it presents the design and implementation of an RNN model for the task that uses BERT embeddings to define contextual word and contextual sentence embeddings as attributes, which to the best of our knowledge were never used before for detecting ongoing events in news; (3) it presents an extensive empirical evaluation that includes (i) the exploration of different architectures and hyperparameters, (ii) an ablation test to study the impact of each attribute, and (iii) a comparison with a replication of a state-of-the-art model. The results offer several insights into the importance of contextual embeddings and indicate that the proposed approach is effective in the OED task, outperforming the baseline models.