tags:

views:

84

answers:

2

Hi everyone!

I am looking for a parser (or generated parser) in java that is capable of followings:

1- I will provide sentences that are already part-of-speech tagged. I will use my own tag set. 2- I don't have any statistical data. So if the parser is statistical, I want to be able to use it without this feature. 3- Adaptable to other languages easily. Low learning curve

My question is a bit similar to this one

http://stackoverflow.com/questions/88984/your-favorite-natural-language-parser

But there isn't any satisfying answer there. Thanks.

A: 

I'm not very clear on what you'd want, but the first thing I thought of was Mallet:

http://mallet.cs.umass.edu/index.php

Andrew
It seems Mallet library doesn't have a parser.
hrzafer
Mallet is a tool for sequence tagging, also called shallow parsing.
larsmans
+2  A: 
ealdent
Do you know some good document about Stanford Parser except its own page.
hrzafer
I wrote a blog post a long while ago that is a bit of an intro to it and references stuff you might need for the Penn TreeBank:
ealdent
oops, the link: http://mendicantbug.com/2007/10/25/the-noobs-guide-to-parsing/.
ealdent
+1. Stanford Parser is really good, I am using it. It is a statistical NLP tagger based on maximum entropy algorithm.
Skarab