Subscribe
Sign in
Start new thread
EC 2
p/ec-2
Rent Virtual Computers
Visit Product
Chris Messina
Amazon Comprehend — Discover insights and relationships in text
Featured
23
•

Amazon Comprehend is an NLP service that identifies the language of the text; extracts key phrases, places, people, brands, or events; understands how positive or negative the text is; and automatically organizes a collection of text files by topic.

Replies
Martin H. Normark
Isn’t there a way to help teach it to recognize new entities? Without that, moving into any sort of vertical, like legal, would be impossible. SpaCy for Python produces about the same entities as in the example, and has a simple training model. https://spacy.io/
Brian Lee
Time to do the Wikipedia test soon...
Kristian Freeman
If you'd like to play with this technology locally, Stanford CoreNLP is a great open-source framework (GPL license) for NLP processing: https://stanfordnlp.github.io/Co...
Jacob Wallenberg
@imkmf @brennanerbz @martinhn I've played around with a few different packages (CoreNLP + some derivatives, Indicoio, etc.) and was very pleased with the keyword and sentiment features of Comprehend. The sentiment feature especially seems far more accurate.
Brennan Erbeznik
@imkmf @geteighty @jrwallenberg what’s remarkable is that not much has changed since the 1990s when the Stanford parser was born. We’re still only doing basic entity and sentiment analysis. Where’s the meaning?
Jacob Wallenberg
@imkmf @geteighty @brennanerbz I can't speak for how sophisticated it was back then, but I find this stuff super helpful. I can barely write Python, but I'm able to automatically parse through thousands of customer reviews and extract what they're talking about and how they feel about it with a decent level of accuracy - using completely free resources!
Sebastian Dobrincu
This has the potential to make NLP somewhat more mainstream among tech companies. Curious to see what the adoption will look like.
Bernardo de Castro
Does anyone have any business ideas, what could they do with it?
Andy Newton
@bernardocastro As an agency marketer, I see a goldmine. Could this be used for aggregating voice of customer data and summarizing a business's ideal customer experience in order create high-converting marketing collateral?
Donté Ledbetter
This is very neat!
Charlie Coppinger
I spent a few minutes trying to figure out how this might be useful from a marketing perspective, and here's what I came up with: I recently came across a copy-writing 'hack' of sorts, which involves collecting a large number of negative reviews from a similar product/service to which you are attempting to write sales copy for and using a simple word-density analyser to determine which are the main pain-points that the feedback revolves around. That way, in theory, you can ensure that you're speaking to your audiences actual pains, as opposed to your assumptions of what they are. This could be used for the same purpose, only on steroids 💪🏼
David Bradley, MBA
@thecoppinger Exactly the perspective I was looking at this with. Now, I'll wait for someone to list an iteration of this with their own tool that does that specifically...
Nur Myrza
How about other languages like Russian and Kazakh?
John Gil

Allowing robots to do your creative thinking is an arena for the lazy and vulnerable mind. Of course this will not be understood now because all things new are exciting and the youth of today are unwittingly being drawn into a false collective. The day will come when a significant aspect of the individual identity, the very point of existence, is no more and the individual will lack the self cognizance to ask this question due to unawares. What remains at that point is obedience, a goal that the globalists of the war have been seeking for many centuries. Well done! Everyone has played their role to perfection. My friends remain the anomalies.

Pros:

None

Cons:

This is not blank...

Allen Bruns
Hi, I have developed NLP algorithms for entity and address parsing in Legal Court Documents. Can this help in this field? It took me a long time to develop these modules. I found that nobody has done a very good job in this area....!!!!
Scott Bowler
Here's a screenshot of what Amazon Comprehend looks like/does by the way: https://imgur.com/a/h5H2X Can't wait to experiment with this on www.chooseholly.com - could provide enormous benefit and insights for our users
Samuel Roy
Other providers like Recast.ai and Wit.ai are great at this too. See how Recast automatically find entities like Amazon and even identify "north" and "south": https://imgur.com/a/tD0kn This is what we use for https://producthunt.com/upcoming..., working well I can tell you!
Pretty good service. What else do you add in the future.
Ricardo Prado

I think this product lacks a dashboard showing how your consumption rate is. AWS Comprehend has 3 good features but it's more reasonable to use your own tool.

Pros:

Easy to use

Cons:

Consumption rate is not quite visible

Lack of features

Vladimir B.
The product is great. I created a simple Serverless open source project that you can deploy with a one-liner and it can parse whole websites for you. Check it out: https://github.com/vbudilov/webs...