You Asked, We Listened: Watson Natural Language Classifier Announcements

With the IBM THINK conference happening in Las Vegas, there are a lot of things to be excited about. In preparation for THINK, Watson Natural Language Classifier is rolling out new features available today, for users to try out.

Classify Multiple Phrases

Reaching out to users and hearing their pain-points is key in product development. One of the customer pain-points focused on having the ability to train and classify data at faster speeds. Today, making API calls to Watson Natural Language Classifier just got easier.

Traditionally, a user had to submit the text to be classified sequentially. The new “classify multiple phrases method” supports sending up to 30 text phrases in one request, saving users time when calling the API.

Specifically, the API endpoint seen below will allow for users to try this new feature for the classification of multiple phrases in the same language.

POST /v1/classifiers/{classifier_id}/classify_collection

Currently, Watson Natural Language Classifiers multiple phrase classification supports the following languages: English, Arabic, French, German, Italian, Japanese*, Korean, Portuguese (Brazilian), and Spanish.

*Japanese support for classifying multiple phrases is in beta.

Curious to try it yourself? Visit our API Reference to see how its done!

Training with larger data sets

Another request we heard was the ability to train with larger datasets. Initially when training a model of Watson Natural Language Classifier, the limit of rows per csv file was 15,000. We are happy to announce we have taken steps towards increasing this limit and it has increased to 20,000. More training data will result in stronger classifier models. Utilizing IBM’s Deep Learning as a Service, the larger datasets will leverage graphic processing units (GPUs) for improved training times.

Note: The maximum size of training data remains at 15,000 records for users in the Frankfurt region or those with IBM Cloud Dedicated.

Attending THINK?

In addition to these key feature announcements there will be key labs and speaker sessions showing how Watson Natural Language Classifier is being applied. Here are some interesting ones to check out:

ICD-10 Code Classification with Watson Natural Language Classifier

Thursday, 8:30 AM — 10:10 AM | Session ID: 8620A

Can’t make it? No worries, try it out yourself by watching the Youtube Video or visiting the GitHub Repo.

Disclaimer: This application is used for demonstrative and illustrative purposes only and does not constitute an offering that has gone through regulatory review. A trained model is only as good as the training data it recieves.

Why Identity Guard Chose Watson Natural Language Classifier for Its News Alerting System

Thursday, 8:30 AM — 9:10 AM | Session ID: 8071A