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...
Statistical parsers trained and tested on the Penn Wall Street Journal (WSJ) treebank have shown vast improvements over the last 10 years. Much of this improvement, however, is ba...
We investigate a number of approaches to generating Stanford Dependencies, a widely used semantically-oriented dependency representation. We examine algorithms specifically design...
Daniel Cer, Marie-Catherine de Marneffe, Daniel Ju...