Paco Escamilla

Google Cloud Natural Language API - Natural language API using Google machine learning

by

Add a comment

Replies

Best
Chafik H'nini
Do you know when it is available for French language ?
Alexandre Sartini
@ch4fik definitely waiting for French as well
Apoorv Saxena
@ch4fik We are working on adding additional language support in near future. Stay tuned.
Chafik H'nini
@apoorvsaxena1 As I am curious, what is the process of supporting a new language ? Are there language-specific rules like grammar to implement or is it just filling a kind of dictionary ?
Daniel F Lopes
"Initial support for English, Spanish and Japanese. It includes: * Sentiment Analysis: Understand the overall sentiment of a block of text * Entity Recognition: Identify the most relevant entities for a block of text and label them with types such as person, organization, location, events, products and media * Syntax Analysis: Identify parts of speech and create dependency parse trees for each sentence to reveal the structure and meaning of text" The amount of applications is enormous. 💪
Miron Vranjes
This is exactly what I've been looking for! Right now, LUIS and Wit.ai mostly require you to route your entire chat stream through them, making it difficult to do hybrid approaches where you can clean up chat structure via pattern matching and then try and decipher using NLP. An alternative approach is to use Stanford's CoreNLP for this, but the sheer size of it makes it impractical for some cloud deployments like Heroku so a REST API is nicer. I'm curious to see how their NER compares to the Stanford one--the auto-retrieval of wikipedia URLs is a nice touch.
Apoorv Saxena
@mironv Look forward to your feedback!
Rotem Yakir
Mohit Gangrade
I knew it. I knew that Google will come up with a Natural Language API. =D So many companies are doing this, how can Google stay behind.
DOUGLΛS Ɇ. ROGERS
Hrm... the only thing that trended negative in a Bernie speech excerpt is a mention of gays in a list of other things marked as positive sentiment.
Apoorv Saxena
@glowingrec Sentences with low magnitude should be interpreted as mixed sentiment. You need to look at the combination of polarity and magnitude to determine sentiment.
Carlos Delgado
Interesting tool! Bot Age!
Giulio Andreini
Very cool! I used this https://dandelion.eu/semantic-te... but this new Google service look quite interesting. Glad to see they connected it to Wikipedia resources (I was afraid they could have connected it to their own resource base - ex freebase)
Uri Eliabayev
The most interesting thing for me was the "Entity Recognition". It can make such a huge change for bot developers
12
Next
Last