Natural Language Basics with TextBlob
11–20 of 24 posts
Re: Natural Language Basics with TextBlob
#12Re: Natural Language Basics with TextBlob
#13Also have a look at http://spacy.io/ It's better than textblob / nltk in many ways.
Sorry, it doesn't seem that better to me.
Re: Natural Language Basics with TextBlob
#14I think NLP is really cool, but it seems to be moving so quickly. If I wanted to get a decent overview, are there some review papers or textbooks with good coverage that aren't too out of date?
I'm a NLP person, and I think the Wit.ai people said it best:
Many papers were kind of “the state of the art for X was Y. We replaced the hand-crafted, manually hacked, heavily engineered Z by a RNN. It improved state of the art by 5 points.” The poor guys who presented deep learning-free papers invariably got the question: “did you also try with a [insert deep net technique here]?”[1]
The only downside with this is that traditional NLP tools are still probably easier to use, and you'll usually need to understand vocabulary to be able to talk to other people about your problems.
Re: Natural Language Basics with TextBlob
#15Also have a look at http://spacy.io/ It's better than textblob / nltk in many ways.
Can you (or someone) comment on some of the important differences, in your mind? I'm quite new to NLP, so a knowledgable comparison of the two would be appreciated :)
EDIT: From today on spacy is free for commercial use! (MIT license).
Re: Natural Language Basics with TextBlob
#16TextBlob is just an easy-to-use wrapper for a number of more involved libraries, including NLTK and Pattern. As with most things like it, if you're looking to shift off extremely unsophisticated NLP work to a junior developer, this is a good thing. If you're an engineer focused in the NLP space, using this API would be like tying your hand behind your back. It introduces its own performance problems, and obscures a n…
If you're doing NLP in Python, there's no reason to use CoreNLP's parser from the NLTK wrapper. Communicating with the Java process over the file system or a socket introduces a tonne of unnecessary complications, slow-downs, invites encoding problems, etc. spaCy's native Cython dependency parser is both faster and more accurate than CoreNLP. The NP chunks example from the post: >>> from spacy.en import English >>> n…
edit: sorry, I just noticed that it is available for free under the AGPL 3 license.
Re: Natural Language Basics with TextBlob
#17This is a particularly beautiful articulation of the complexity of English (and language in general).
Re: Natural Language Basics with TextBlob
#18Earlier quoted context omitted.
If you're doing NLP in Python, there's no reason to use CoreNLP's parser from the NLTK wrapper. Communicating with the Java process over the file system or a socket introduces a tonne of unnecessary complications, slow-downs, invites encoding problems, etc. spaCy's native Cython dependency parser is both faster and more accurate than CoreNLP. The NP chunks example from the post: >>> from spacy.en import English >>> n…
spaCy looks like a great product, but it is expensive. edit: sorry, I just noticed that it is available for free under the AGPL 3 license.
Re: Natural Language Basics with TextBlob
#19Also have a look at http://spacy.io/ It's better than textblob / nltk in many ways.
"English only (at present)" Sorry, it doesn't seem that better to me.
In most NLP libraries, you have to decode two things: what exists, and what you can actually build against. Often the first is well documented, but for the second you might be left with no comment at all, even if the model does not produce output usefully better than chance. You just have to try it out and see for yourself.
Multi-lingual support is not there yet. But when it is it'll be good.
Multi-lingual support is an important issue, and a key reasons I decided to relocate from Sydney and base the business in Berlin. My new co-founder, Henning Peters, is a native speaker of German.
Re: Natural Language Basics with TextBlob
#20Earlier quoted context omitted.
spaCy looks like a great product, but it is expensive. edit: sorry, I just noticed that it is available for free under the AGPL 3 license.
Now 100% free under the MIT license. Things change by the hour in spacy world, :-).