Name perplexity

Abstract

The accuracy of a Cross Document Coreference system depends on the amount of context available, which is a parameter that varies greatly from corpora to corpora. This paper presents a statistical model for computing name perplexity classes. For each perplexity class, the prior probability of coreference is estimated. The amount of context required for coreference is controlled by the prior coreference probability. We show that the prior probability coreference is an important factor for maintaining a good balance between precision and recall for cross document coreference systems.