Forest Reranking: Discriminative Parsing with Non-Local Features

Conventional n-best reranking techniques often suffer from the limited scope of the nbest list, which rules out many potentially good alternatives. We instead propose forest reranking, a method that reranks a packed forest of exponentially many parses. Since exact inference is intractable with non-local features, we present an approximate algorithm inspired by forest rescoring that makes discriminative training practical over the whole Tree

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Liang Huang
• Keywords: ACL 2008, Computational Linguistics, Exact Inference, Limited Scope, Packed Forest