[Update 14 Sep] Several people have asked what tools/data are allowed for the rule-based tagger and for the "do as well as you can" part. Here is an attempt to clarify. My goal isn't to make life hard on you, but to not give unfair advantages to some subsets of the class.
- For the rule-based tagger, any rules are fair game, but it would be better if you made your tagger WITHOUT looking at the labeled training data. That is, feel free to look at the sentences, but pretend that you don't have access to the tags. After all, that's how it would be in the real world. Yes, this means that you'll have to use some linguistics. That's not a terrible thing :).
- For the last part of the project, where you have to build the best tagger possible, people have asked about using external tools. For this project, I would ask that anything you use beyond normal library / unix tools stuff, you implement yourself. Yes, you could probably do better using well-engineered tools, but that probably won't help you learn as much as you will if you do something slightly less good, but do it on your own.
- (Note that this final rule will not be the case for the final class project: there, anything is fair game!)
Is the project due the 28th or the 30th? Its 28th on the class website and 30th here....
ReplyDeleteSince the submission system shows 22 days left, I guess it should be 30th.
ReplyDeleteI am looking for a partner for project 1. I'm a CompSci graduate student. Please respond to me by email: cgiannella@mitre.org
ReplyDeleteTwo CS students are looking for a partner with a Linguistics background. You can send mail to my umd.edu address, where my user id is "puuj"
ReplyDeleteI just edited this post to clarify some "fair use" issues for the project.
ReplyDelete