Understanding Robocup-Soccer Narratives
Hannaneh Hajishirzi, Eyal Amir · 2011
We present an approach to map Robocup-soccer narratives (in natural language) to a sequence of meaningful events and use them to answer semantic questions about the narratives. Our approach takes advantage of an action-centered framework, an inference subroutine, and an iterative learning algorithm. Our framework represents the narrative as a sequence of sentences and each sentence as a probability distribution over deterministic events. Our learning algorithm maps sentences to meaningful events without any annotated labeled data. Instead, it uses a prior knowledge about event descriptions and an inference subroutine to estimate initial training labels. The algorithm further improves the training labels at next iterations. In our experiments we demonstrate that with no labeled data our algorithm achieves higher accuracy compared to the state of the art that uses labeled data. 1