Pricing plans
| Plan | Features | Pricing | |
|---|---|---|---|
Summary
The Natural Language Classifier service uses advanced natural language processing and machine learning techniques to assign custom categories to inputted text. For example, you submit a question and the service returns keys to the best matching answers or next actions for your application. You create a classifier instance by providing a set of representative strings and a set of one or more correct classes for each training. After training, the new classifier can accept new questions or phrases and return the top matches with a probability value for each match.
Features
Train and classify in multiple languages
English, Arabic, French, German, Italian, Japanese, Korean, Portuguese (Brazilian), and Spanish.
Classify natural language text
Train classifiers with text phrases, each with a maximum of 1024 characters
Leverage IBM Deep Learning as a Service during training
Each .csv file used in training can contain up to 20,000 records.
Create up to 8 classifiers with each Natural Language Classifier service instance
Multi-Category classification
Extract multiple categories from text phrases
Multi-Phrase classification
Classify up to 30 separate text phrases in a single request with the classify collection endpoint. Charged at $0.0035/text phrase.
Media
Using the Service