Opennlp vs stanford nlptools vs berkeley

Question

Hi, the goal is to parse a large body, such as wikipedia, to generate the most likely parsing tree and called entity recognition. What is the best library to achieve this in terms of performance and accuracy? Has anyone used more than one of the above libraries?

Answer 1

I am currently using the Enju HPSG parser, which seems to be better than others.

Answer 2

In my experiments, I use Streetford tester, but it really depends on the quality of your Wikipedia articles. Here you will find a comparison of various tagging of-speech - PoS tags on aclweb .

Answer 3

Refer to this article: http://nlp.stanford.edu/pubs/lrecstanforddeps_final_final.pdf