SERC: Syntactic and Semantic Sequence based Event Relation Classification

TL;DR

This paper introduces SERC, a joint LSTM-based model that leverages syntactic and semantic features to classify temporal and causal relations between events, improving understanding of event dependencies.

Contribution

It proposes a novel joint model that combines syntactic and semantic features for simultaneous classification of temporal and causal event relations.

Findings

Promising results on four datasets.

Effective integration of syntactic and semantic features.

Improved classification accuracy for event relations.

Abstract

Temporal and causal relations play an important role in determining the dependencies between events. Classifying the temporal and causal relations between events has many applications, such as generating event timelines, event summarization, textual entailment and question answering. Temporal and causal relations are closely related and influence each other. So we propose a joint model that incorporates both temporal and causal features to perform causal relation classification. We use the syntactic structure of the text for identifying temporal and causal relations between two events from the text. We extract parts-of-speech tag sequence, dependency tag sequence and word sequence from the text. We propose an LSTM based model for temporal and causal relation classification that captures the interrelations between the three encoded features. Evaluation of our model on four popular datasets yields promising results for temporal and causal relation classification.