WEBVTT 00:00:00.000 --> 00:00:00.933 Hi, everyone. 00:00:00.933 --> 00:00:05.521 We know that most of you still working really hard on the last couple of assignments and problem sets 00:00:05.521 --> 00:00:12.110 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. 00:00:12.110 --> 00:00:14.815 And first of all, everyone is always interested in numbers 00:00:14.815 --> 00:00:17.092 so let’s say a bit about the numbers. 00:00:17.092 --> 00:00:24.441 So, it seems like, as we come into week 7’s material of the problem sets and programming assignments, 00:00:24.441 --> 00:00:28.416 it seems like there are about 5,000 people still actively watching the videos 00:00:28.416 --> 00:00:32.423 and about 2,000 people doing all the work of the homeworks. 00:00:32.423 --> 00:00:37.186 But that’s, you know, overall it’s just been an enormous amount of stuff going on 00:00:37.186 --> 00:00:40.626 so it now have well over a million video views and all. 00:00:40.626 --> 00:00:43.186 Yeah, it’s very exciting. 00:00:43.201 --> 00:00:47.464 Programming homework six, the parsing homework, was definitely our hardest homework so far 00:00:47.464 --> 00:00:50.468 and there were definitely problems with the code being under-commented 00:00:50.468 --> 00:00:53.571 so we appreciate very much those of you who helped out each other in the forums 00:00:53.571 --> 00:00:56.674 and made things very clear for each other. 00:00:56.674 --> 00:01:01.205 Those of you who managed to finish the homework have told us they got a lot out of it. 00:01:01.205 --> 00:01:04.366 But those of you who didn’t have the time to do all of it, 00:01:04.366 --> 00:01:07.318 we encourage you to do come back and do programming homework seven and eight 00:01:07.318 --> 00:01:11.178 which are much easier than homework six and should be a lot fun as well. 00:01:11.178 --> 00:01:14.526 One of the things that some people have been asking about is, 00:01:14.526 --> 00:01:18.831 “Hey, can we take those great parsers that we did write for programming assignment six 00:01:18.831 --> 00:01:23.762 and keep on working on them by posting them on Github or some other site like that?” 00:01:23.762 --> 00:01:26.964 There is a slight problem with that because, you know, 00:01:26.964 --> 00:01:29.943 we are hoping that we’ll be able to do this course again some time in the future 00:01:29.943 --> 00:01:32.272 and we’d like to be able to reuse some of the assignments 00:01:32.272 --> 00:01:37.723 so I’d really prefer that there just aren’t great solutions to all the assignments sitting on the open web 00:01:37.723 --> 00:01:41.870 and to keep some of that stuff on the forum sites for the class. 00:01:41.870 --> 00:01:46.526 So, it’s great that people want to keep exploring and doing better things for NLP 00:01:46.526 --> 00:01:50.135 but we’d really think it’s probably a better idea for you 00:01:50.135 --> 00:01:53.745 to pick up one of the several open source NLP frameworks that’re out there 00:01:53.745 --> 00:01:56.542 and look at ways in which you can contribute to that 00:01:56.542 --> 00:01:59.370 ’cause that both doesn’t sort of conflict with our assignments 00:01:59.370 --> 00:02:03.591 but that’s actually going to be more useful for you and people around the world in general 00:02:03.591 --> 00:02:05.941 if you’re helping along these open source frameworks. 00:02:05.941 --> 00:02:09.585 So there are good ones — For Python NLTK is the best-known one; 00:02:09.585 --> 00:02:13.350 and there are several well-known Java NLP open source frameworks 00:02:13.350 --> 00:02:16.509 which certainly includes our own Stanford NLP tools 00:02:16.509 --> 00:02:20.636 but also other things like OpenNLP, the GATE NLP Framework; 00:02:20.636 --> 00:02:24.194 components: UIMA — a bunch of stuff out there if you look around. 00:02:24.963 --> 00:02:31.394 Okay and that brings up the issue of what’s going to happen with this class website after the class ends. 00:02:31.394 --> 00:02:33.806 It is going to stay open and available 00:02:33.806 --> 00:02:37.656 and all you guys will be able to keep on looking at stuff and referencing things 00:02:37.656 --> 00:02:43.021 and even beyond that, what we’re also going to have is this going to be available in an archive mode. 00:02:43.021 --> 00:02:46.153 So, people who haven’t been registered in the class 00:02:46.153 --> 00:02:50.227 will also be able to look at the content in terms of the videos that are up there 00:02:50.227 --> 00:02:52.605 but not the programming assignments 00:02:52.605 --> 00:02:56.030 which we are kind of going to keep to the people who were enrolled in the class. 00:02:56.030 --> 00:02:58.387 But you shouldn’t worry about things going away. 00:02:58.387 --> 00:03:00.413 Yes and those of you who are enrolled can still — 00:03:00.413 --> 00:03:02.412 the forum will stay up — 00:03:02.412 --> 00:03:05.375 we encourage you to continue to talk to each other on the forums. 00:03:05.375 --> 00:03:07.819 Those of you who never got to finish some of the homeworks, 00:03:07.819 --> 00:03:09.313 keep working on the homeworks, 00:03:09.313 --> 00:03:11.733 go ahead and post them. The site will stay up. 00:03:11.733 --> 00:03:16.055 And then for new people we will eventually be teaching the class again 00:03:16.055 --> 00:03:18.300 but meanwhile we’ll be leaving the videos up 00:03:18.300 --> 00:03:21.068 so if your friends want to watch the videos, we encourage that. 00:03:21.068 --> 00:03:24.583 And then eventually we’ll actually teach the class again. 00:03:24.583 --> 00:03:29.747 In fact for everybody, it’s been really helpful on the forums there — 00:03:29.747 --> 00:03:33.168 we mentioned this earlier about helping people out with the code, 00:03:33.168 --> 00:03:35.923 helping people out with basic NLP. 00:03:35.923 --> 00:03:39.960 It’s been very supportive community and we really appreciate that and we think it’s really great. 00:03:39.960 --> 00:03:42.808 We’d like help from you in suggesting — 00:03:42.808 --> 00:03:46.983 you have already given us suggestions for next year but I’ve put up a forum just now 00:03:46.983 --> 00:03:51.926 that we’d like you, give us specific suggestions about ways we can make the course better for next year. 00:03:51.926 --> 00:03:53.815 We know Homework six is one of them 00:03:53.815 --> 00:03:57.377 but there’s lot of suggestions you’ve given about improving the problem sets 00:03:57.377 --> 00:03:59.907 or other reading material we can suggest 00:03:59.923 --> 00:04:03.559 or anything else that will help us improve our course for the second time we teach it 00:04:03.559 --> 00:04:05.740 that would be great. 00:04:06.356 --> 00:04:12.866 We all have dreams of the future where there are computers with full natural language understanding 00:04:12.866 --> 00:04:16.473 and in our research we still variously hoped to work to those goals 00:04:16.473 --> 00:04:21.992 but in terms of the practical NLP that’s deployed around the world at the moment, 00:04:21.992 --> 00:04:25.391 really you guys are just seeing the ton of the stuff that are actually used. 00:04:25.391 --> 00:04:30.590 Things like text classifiers, building sequence classifiers, named entities and other things, 00:04:30.590 --> 00:04:34.530 parsers, questions answering, machine techniques,… 00:04:34.530 --> 00:04:37.429 So you really should feel good if you’ve made your way through this class 00:04:37.429 --> 00:04:41.974 that you are a competent practitioner of the kind of useful NLP techniques 00:04:41.974 --> 00:04:47.515 that’re leading to a new class of more intelligent language-wielding computer applications 00:04:47.515 --> 00:04:51.188 and so we hope that you’ll be able to take these ideas and knowledge, 00:04:51.188 --> 00:04:56.227 and go off and apply them in many different places. 00:04:56.227 --> 00:05:01.481 We clearly are in this world now where human language material is just everywhere over the web 00:05:01.481 --> 00:05:06.929 as part of the new move to the content authoring and social computing that’s going on everywhere. 00:05:06.929 --> 00:05:09.378 So much of that is about language use. 00:05:09.378 --> 00:05:13.088 So now you have a good toolkit to be able to go off and do things with that material 00:05:13.088 --> 00:05:16.011 and we hope that you’ll be able to find good things to do. 00:05:16.011 --> 00:05:21.154 Yeah. Thanks for taking the class and look forward to seeing you wherever and whenever we see you. 00:05:21.154 --> 99:59:59.999 Thanks a lot.