Incorporating Structured Commonsense Knowledge in Story Completion
This addresses the problem of narrative comprehension for AI systems by explicitly incorporating commonsense knowledge, though it is incremental as it builds on existing story completion methods.
The paper tackled story ending prediction by integrating narrative sequence, sentiment evolution, and commonsense knowledge into a neural model, achieving state-of-the-art performance on the ROCStory Cloze Task with significant gains from the added knowledge.
The ability to select an appropriate story ending is the first step towards perfect narrative comprehension. Story ending prediction requires not only the explicit clues within the context, but also the implicit knowledge (such as commonsense) to construct a reasonable and consistent story. However, most previous approaches do not explicitly use background commonsense knowledge. We present a neural story ending selection model that integrates three types of information: narrative sequence, sentiment evolution and commonsense knowledge. Experiments show that our model outperforms state-of-the-art approaches on a public dataset, ROCStory Cloze Task , and the performance gain from adding the additional commonsense knowledge is significant.