Skip to main content
Natural Language Toolkit

Natural Language Toolkit

Computer programWikipedia

Search complete. 12 mentions across 4 episodes found for "Natural Language Toolkit".

Nov 14, 2026

Harrison KinsleyHOST
9:35
Um, I could try that.
Harrison KinsleyHOST
9:37
Uh, I just don't know enough about, uh, that package to know if, if I can do what I'm thinking of, but I'm sure I can, but I know like with NLTK, um, I could use NLTK to know, is this a complete sentence? Is it a coherent thought? So that would be a really good way to score outputs.
Harrison KinsleyHOST
9:53
My curiosity is how quickly I can do that.
Harrison KinsleyHOST
9:56
But that will probably be the next step after I do what I'm thinking of doing today because there are far easier ways to judge these outputs.

24 MINS LATER

Harrison KinsleyHOST
34:17
I dot strip.
Harrison KinsleyHOST
34:18
There's got to be a better way than this.
Harrison KinsleyHOST
34:20
Again, if you were using NLTK and I'm sure Spacey, you could just say like tokenize.
Harrison KinsleyHOST
34:24
Okay.
David ShapiroHOST
19:10
But NLP stuff was still much cheaper.
David ShapiroHOST
19:13
NLTK could run on a calculator.
David ShapiroHOST
19:15
GPT-3 could not run on a calculator.
David ShapiroHOST
19:17
So its utility per dollar was actually lower than other NLP processing technologies like NLTK and those sorts of things.
David ShapiroHOST
19:26
So GPT-3 was actually not worth using for basic NLP tasks, it was still good for list generation, summarization, and a few very, very small tasks.
David ShapiroHOST
19:39
But remember that you were limited at first to 1,000 tokens and then 2,000 tokens.
Christopher PottsHOST
23:54
Uh, Bing Liu's opinion lexicon is just two word list, positive, negative.
Christopher PottsHOST
23:59
You're gonna work with it on homework one because it's built into NLTK.
Christopher PottsHOST
24:02
And it's really nice in the sense that it does a good job of classifying words in a pretty context independent way, and it's pretty well attuned to the kind of data that you might see on the web.
Christopher PottsHOST
24:13
Uh, SentiWordNet is a project of adding sentiment information to WordNet.
Christopher PottsHOST
24:18
And so if you're already doing work in WordNet, it's a kind of nice counterpart.
Christopher PottsHOST
24:21
Uh, and NLTK has a SentiWordNet reader, which actually I wrote.
Christopher PottsHOST
24:26
Um, The MPQA subjectivity lexicon is a kind of classic and if you follow that link, you'll see that that group released a bunch of datasets related to sentiment.
Christopher PottsHOST
24:35
Uh, the Harvard General Inquirer is just a huge spreadsheet of words along the rows and then lots of different affective and other social dimension measured along the columns.
Harrison KinsleyHOST
3:11
And so that concludes pretty much the installation.
Harrison KinsleyHOST
3:14
But again, just like my NLTK tutorial, I feel bad making the first video being only the installation.
Harrison KinsleyHOST
3:20
So let's make our first window at WXPython.
Harrison KinsleyHOST
3:24
So of course, to use WXPython, you'll need to import WX.

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.