**This is an old revision of the document!**


Setting Up Your System For ALFA

(Disclaimer: I am not particularly familiar with Wiki format so someone is welcome to clean this all up) <br/> <br/> Setting up your system for running the ALFA project is straight forward. <br/> <br/> Projects <br/> Download the following two projects in whichever SVN client you prefer. <ol> <li>StatNLP - http://nlp.cs.byu.edu/subversion/statnlp</li> <li>ALFA - http://nlp.cs.byu.edu/subversion/alfa</li> </ol> <br/> Data <br/> Once you have downloaded the two projects you will need to get data. Currently I have been using the Penn Treebank but hopefully we will have some poetry data soon. The Penn Treebank data that I have been using is available on Entropy in http://nlp.cs.byu.edu/data/alfa/PennTreeBank.zip . This includes three files: 1) Training, 2) Validation, and 3) Test. These files have been modified to the format WORD_TAG. That is what will be required to use the modified reader in the ALFA project <br/> <br/> Running Experiments <br/><br/> I have included various experiment XML configuration files in the project. You will need to modify those to reflect the setup on your machine. I have tried to comment the ALFA project to make it more useful. <br/><br/> Problems <br/> If you have problems connecting it is most likely one of two problems: <ol> <li>You don't have permissions. To fix this it is probably best to talk to Dr. Ringger or Robbie</li> <li>You connected the the SVN server previously with a username and password that has been cached. To fix this see Robbie's blog

nlp-private/alfa-setup.1429821546.txt.gz · Last modified: 2015/04/23 14:39 by ryancha
Back to top
CC Attribution-Share Alike 4.0 International
chimeric.de = chi`s home Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0