Learning Fine-Grained Knowledge about Contingent Relations between Everyday Events

TL;DR

This paper introduces a novel method for extracting fine-grained causal and conditional relationships between everyday events from social media stories, improving understanding for various NLP tasks.

Contribution

It presents a new approach for learning detailed contingency knowledge from stories and demonstrates the benefits of topic-specific datasets over general-domain data.

Findings

Topic-specific datasets improve the granularity of learned event relations.

82% of learned relations are judged as contingent by human evaluators.

Method outperforms baselines in learning event contingency relations.

Abstract

Much of the user-generated content on social media is provided by ordinary people telling stories about their daily lives. We develop and test a novel method for learning fine-grained common-sense knowledge from these stories about contingent (causal and conditional) relationships between everyday events. This type of knowledge is useful for text and story understanding, information extraction, question answering, and text summarization. We test and compare different methods for learning contingency relation, and compare what is learned from topic-sorted story collections vs. general-domain stories. Our experiments show that using topic-specific datasets enables learning finer-grained knowledge about events and results in significant improvement over the baselines. An evaluation on Amazon Mechanical Turk shows 82% of the relations between events that we learn from topic-sorted stories are judged as contingent.