Reranking the Berkeley and Brown Parsers

The Brown and the Berkeley parsers are two state-of-the-art generative parsers. Since both parsers produce n-best lists, it is possible to apply reranking techniques to the output of both of these parsers, and to their union. We note that the standard reranker feature set distributed with the Brown parser does not do well with the Berkeley parser, and propose an extended set that does better. An ablation experiment shows that different parsers benefit from different reranker features.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Mark Johnson, Ahmet Engin Ural
• Keywords: Berkeley Parser, Computational Linguistics, NAACL 2010, Parsers, State-of-the-art Generative Parsers