-
Hi, everyone.
-
We know that most of you still working really hard on the last couple of assignments and problem sets
-
but nevertheless our NLP class is coming to its close and so we thought we’ll both update you on a few of the issues.
-
And first of all, everyone is always interested in numbers
-
so let’s say a bit about the numbers.
-
So, it seems like, as we come into week 7’s material of the problem sets and programming assignments,
-
it seems like there are about 5,000 people still actively watching the videos
-
and about 2,000 people doing all the work of the homeworks.
-
But that’s, you know, overall it’s just been an enormous amount of stuff going on
-
so it now have well over a million video views and all.
-
Yeah, it’s very exciting.
-
Programming homework six, the parsing homework, was definitely our hardest homework so far
-
and there were definitely problems with the code being under-commented
-
so we appreciate very much those of you who helped out each other in the forums
-
and made things very clear for each other.
-
Those of you who managed to finish the homework have told us they got a lot out of it.
-
But those of you who didn’t have the time to do all of it,
-
we encourage you to do come back and do programming homework seven and eight
-
which are much easier than homework six and should be a lot fun as well.
-
One of the things that some people have been asking about is,
-
“Hey, can we take those great parsers that we did write for programming assignment six
-
and keep on working on them by posting them on Github or some other site like that?”
-
There is a slight problem with that because, you know,
-
we are hoping that we’ll be able to do this course again some time in the future
-
and we’d like to be able to reuse some of the assignments
-
so I’d really prefer that there just aren’t great solutions to all the assignments sitting on the open web
-
and to keep some of that stuff on the forum sites for the class.
-
So, it’s great that people want to keep exploring and doing better things for NLP
-
but we’d really think it’s probably a better idea for you
-
to pick up one of the several open source NLP frameworks that’re out there
-
and look at ways in which you can contribute to that
-
’cause that both doesn’t sort of conflict with our assignments
-
but that’s actually going to be more useful for you and people around the world in general
-
if you’re helping along these open source frameworks.
-
So there are good ones — For Python NLTK is the best-known one;
-
and there are several well-known Java NLP open source frameworks
-
which certainly includes our own Stanford NLP tools
-
but also other things like OpenNLP, the GATE NLP Framework;
-
components: UIMA — a bunch of stuff out there if you look around.
-
Okay and that brings up the issue of what’s going to happen with this class website after the class ends.
-
It is going to stay open and available
-
and all you guys will be able to keep on looking at stuff and referencing things
-
and even beyond that, what we’re also going to have is this going to be available in an archive mode.
-
So, people who haven’t been registered in the class
-
will also be able to look at the content in terms of the videos that are up there
-
but not the programming assignments
-
which we are kind of going to keep to the people who were enrolled in the class.
-
But you shouldn’t worry about things going away.
-
Yes and those of you who are enrolled can still —
-
the forum will stay up —
-
we encourage you to continue to talk to each other on the forums.
-
Those of you who never got to finish some of the homeworks,
-
keep working on the homeworks,
-
go ahead and post them. The site will stay up.
-
And then for new people we will eventually be teaching the class again
-
but meanwhile we’ll be leaving the videos up
-
so if your friends want to watch the videos, we encourage that.
-
And then eventually we’ll actually teach the class again.
-
In fact for everybody, it’s been really helpful on the forums there —
-
we mentioned this earlier about helping people out with the code,
-
helping people out with basic NLP.
-
It’s been very supportive community and we really appreciate that and we think it’s really great.
-
We’d like help from you in suggesting —
-
you have already given us suggestions for next year but I’ve put up a forum just now
-
that we’d like you, give us specific suggestions about ways we can make the course better for next year.
-
We know Homework six is one of them
-
but there’s lot of suggestions you’ve given about improving the problem sets
-
or other reading material we can suggest
-
or anything else that will help us improve our course for the second time we teach it
-
that would be great.
-
We all have dreams of the future where there are computers with full natural language understanding
-
and in our research we still variously hoped to work to those goals
-
but in terms of the practical NLP that’s deployed around the world at the moment,
-
really you guys are just seeing the ton of the stuff that are actually used.
-
Things like text classifiers, building sequence classifiers, named entities and other things,
-
parsers, questions answering, machine techniques,…
-
So you really should feel good if you’ve made your way through this class
-
that you are a competent practitioner of the kind of useful NLP techniques
-
that’re leading to a new class of more intelligent language-wielding computer applications
-
and so we hope that you’ll be able to take these ideas and knowledge,
-
and go off and apply them in many different places.
-
We clearly are in this world now where human language material is just everywhere over the web
-
as part of the new move to the content authoring and social computing that’s going on everywhere.
-
So much of that is about language use.
-
So now you have a good toolkit to be able to go off and do things with that material
-
and we hope that you’ll be able to find good things to do.
-
Yeah. Thanks for taking the class and look forward to seeing you wherever and whenever we see you.
-
Thanks a lot.