Custom Classifier

Your Data. Your Categories. Your Classifier without any training !

Try our Custom Classifier demo

Enter Text:

Enter Category:

Custom Classifier

A lot of the times, the biggest hindrance to use Machine learning is unavailability of a data-set. There are many people who want to use AI for categorizing data but that needs making a data-set giving rise to a situation similar to a chicken egg problem.

You don't have data to tag, but you need tagged data to categorize. This makes people give up on using Machine Learning, either scrapping the automation process altogether or using rule based systems. Rule based systems are notorious for making life hell at scale as they cannot be replaced and don't work well at the same time. The right way to solve this is to make Machine Learning systems which can be used from the first day itself and get better with time.

If this was said a couple of years back, it would have been dismissed as a pipe dream, but with recent developments in the field and a few contributions from us to this research, it is now possible !

How our Custom Classifier Works ?

Zero Shot Learning is a way to be able to infer dataset's members without training on it. It is mostly achieved by some form of transfer learning, by which knowledge learned from one dataset can be applied on a different one. While people have proposed multiple zero shot learning approaches for vision tasks where knowledge from imagenet dataset can be used on new ones, we haven't yet seen any example of zero shot learning for text classification.

In our latest research work, we have proposed a method to do zero shot learning on text, where an algorithm trained to learn relationships between sentences and their categories on a large noisy dataset can be made to generalize to new categories or even new datasets. We call the paradigm "Train Once , Test Anywhere". We also propose multiple neural network algorithms that can take advantage of this training methodology and get good results on different datasets. The best method uses an LSTM model for the task of learning relationships. The idea is if one can model the concept of "belongingness" between sentences and classes, the knowledge is useful for unseen classes or even unseen datasets.

Get Your Free text analysis API

Get Free API Key