Learning Fine-Grained Knowledge about Contingent Relations between Everyday Events
This work addresses the need for better text understanding in AI applications like question answering, but it is incremental as it builds on existing methods for learning from stories.
The paper tackled the problem of learning fine-grained common-sense knowledge about contingent relations between everyday events from social media stories, and found that using topic-specific datasets significantly improved performance, with 82% of learned relations judged as contingent in evaluations.
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.