Event Representation Learning Enhanced with External Commonsense Knowledge

TL;DR

This paper enhances event representation learning by integrating external commonsense knowledge about intent and sentiment, significantly improving performance on event similarity, prediction, and stock market volatility tasks.

Contribution

It introduces a novel approach that incorporates external commonsense knowledge into event embeddings, improving their effectiveness for various downstream tasks.

Findings

78% improvement on hard event similarity task

More accurate inferences for subsequent events

Better stock market volatility predictions

Abstract

Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction. On the other hand, events extracted from raw texts lacks of commonsense knowledge, such as the intents and emotions of the event participants, which are useful for distinguishing event pairs when there are only subtle differences in their surface realizations. To address this issue, this paper proposes to leverage external commonsense knowledge about the intent and sentiment of the event. Experiments on three event-related tasks, i.e., event similarity, script event prediction and stock market prediction, show that our model obtains much better event embeddings for the tasks, achieving 78% improvements on hard similarity task, yielding more precise inferences on subsequent events under given contexts, and better accuracies in predicting the volatilities of the stock market.