Text Classification: Binary to Multi-label Multi-class classification

Unstructured data in the form of text is everywhere: emails, web pages, social media, survey responses, domain data and more. While textual data is very enriching, it is very complex to gain insights easily and classifying text manually can be hard and time-consuming. For businesses to make intelligent data-driven decisions, understanding the insights in the text in a fast and reliable way is essential. Artificial Intelligence makes that possible with Natural Language Processing (NLP) and text classification. The capability to automatically classify text into one or more categories have seen tremendous improvements in recent years. Gone are the days of manually tagging textual data which can be laborious, time-consuming, inconsistent and expensive.

So let’s look at a few types of text classification in AI.

Binary classification: As the name suggests is the process of assigning a single boolean label to textual data. Example: Reviewing an email and classifying it as good or spam.

AI Binary Classification

Multi-class classification: Multi-class classification involves the process of reviewing textual data and assigning one (single label) or more (multi) labels to the textual data. The complexity of the problem increases as the number of classes increase. Lets take an example of assigning genres to movies. Each movie is assigned one or more genres from a list of movie genres (Drama, Action, Comedy, Horror, etc.). This is a Multi-class classification problem with a manageable set of labels.

AI Multiclass classifiction

 

Now imagine a classification problem where a specific item will need to be classified across a very large category set (10,000+ categories). The problem becomes exponentially difficult. Here is where eXtreme Multi-Label Text Classification with BERT (X-BERT) comes into play. If you want to learn more about Google’s NLP framework BERT, click here.

X-BERT aims to tag each input text with the most relevant labels from an extremely large label set.

Here are a few examples of multi-class classification: Classifying a product in retail to product categories. There are hundreds of thousands of product categories (https://www.researchandmarkets.com/categories) and classifying a single product to one of category based on the product description constitutes a multi-label (specific product category) multi-class ((broader product category) example.

Displaying sponsored content based on user search queries. There are thousands of combinations of ways, users can type in a search query and in order to classify user inputs to display a specific ad under sponsored ads is another extremely large classification example.

AI based MultiLabel classification

In the work we do for the US Navy, we tackle a similar problem of identifying a single equipment name & id from a list of equipment names across ships. The need is to find the right equipment from a list of 50,000+ items with more than 90% accuracy. We utilized X-BERT model connected to additional dense layer and softmax layer to conduct fine-tuning training to identify the equipment. This combined with the subject matter expert validation and verification helped train the machine to get better over time in identifying the equipment.

Extremely Large Multi-class classification X-BERT

As shown in the examples above, with the right methodology and data training, unstructured text can be categorized automatically using AI NLP technology. Employing AI-based auto-classification will make classification more effective and efficient.

Transfer Learning

Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task.

In transfer learning, we leverage prior knowledge from one domain into a different domain. The way transfer learning is done is by deleting the last output layer and creating a new set neural network layers for the new problem. Then these layers are trained using the new data set.

For example, let’s say you have an AI model to recognize cats, now we can use that knowledge to recognize elephants. The model for recognizing cats is created by training the model with pictures of cats (plenty on the internet). Once the model is trained to recognize cats with high accuracy, then the last layer of the neural network will be replaced with additional layers and those layers will be trained using pictures of elephants to recognize elephants. This is done so that a lot of the low-level features like detecting edges, curves, etc. could be learned from the large dataset (in this case Cats) and the newer model will be trained to recognize specific elements (elephants specific features) with fewer data as shown in the below figure.

 

Most of the success today in achieving high accuracy in AI models has been driven by extensive supervised learning which relies on large amounts of labeled datasets. For simple use cases, large amounts of labeled public data is available through various online sources (Ex: ImageNet, WordNet, etc.) but if you are building a model for a specific domain solution, large amounts of labeled data is hard to obtain or data will need to be cleaned and labeled manually for building the model. Transfer learning enables you to develop fairly accurate models using comparatively little data. This is very useful at enterprises that might not have a lot of clean labeled data.

Therefore on some problems where you may not have very much data, transfer learning will enable you to develop skillful models that you simply could not develop in the absence of transfer learning.

Knowledge Integration

Knowledge Integration in AI

So let’s think about how humans learn, we humans are very good at continuously enriching and refining our knowledge and skills by seamlessly combining existing knowledge with new experiences. We exhibit a wide spectrum of learning abilities in various fields. We can be lawyers during the day and go play tennis or go for a run in the evening and make dinner at night. We are fairly adept at doing multiple tasks. When you think about AI systems, that is usually not the case. AI systems are very good at doing a specific task through machine learning alternatively called Narrow Intelligence.

Despite recent breakthroughs and advances, machine learning has a number of shortcomings when it comes to obtaining knowledge in various fields and in developing methods to identify how new and prior knowledge interact to gain more insights. Knowledge integration is the process of synthesizing multiple knowledge representations into a common model. It represents the process of how new information and existing information interact, what effects will the new information will have on existing knowledge and if existing information needs to be modified to accommodate new information.

Why is this concept important? It is important for building a better machine learning model for enterprise knowledge insights.  Not all knowledge will be readily available or can be fed into the machine learning model at once. Substantial knowledge bases are developed incrementally and a growing body of knowledge will need to be added separately. By identifying subtle conflicts and gaps in knowledge, KI facilitates better learning models. Large firms like Google are using a combination of Symbolic AI, Deep learning and Supervised learning to create better knowledge understanding and knowledge reasoning.

If you are an organization looking to extract valuable information and identify patterns within your data to create efficiency, these concepts are critical and I highly recommend doing further research around these to achieving success.

Deep Learning

What is Deep Learning?

Deep Learning is a subset of machine learning that allows machines to do tasks that typically require human like intelligence. The inspiration for deep learning comes from neuroscience, if you look at the architecture of Deep Learning Neural Networks, they are connected in a fundamental way that mirrors the brain. Deep-learning networks are distinguished from the more commonplace neural networks by their depth; that is, the number of node layers through which data passes in a multistep process.

Earlier versions of neural networks were shallow, composed of one input and one output layer, and at most one hidden layer in between. More than three layers (including input and output) qualifies as “deep” learning. So deep as strictly defined means more than one hidden layer.

Neural Network

Deep learning Neural network

In deep-learning networks, each layer of nodes trains on a distinct set of features based on the previous layer’s output. The further you advance into the neural net, the more complex the features your nodes can recognize, since they aggregate and recombine features from the previous layer.

Let’s take a simple example of recognizing hand written numbers from 1 – 10. If 10 people wrote the numbers, the numbers will look very different from each person. For a human brain, it is fairly easy to identify these numbers. For a traditional machine it is impossible to detect and hence Neural Networks are used to mimic the way, neurons in the brain interact. These multiple hidden layers allow a computer to determine the nature of a handwritten digit by providing a way for the neural network to build a rough hierarchy of different features that make up the handwritten digit.

For instance, if the input is an array of values representing the individual pixels in the image of the handwritten figure, the next layer might combine these pixels into lines and shapes, the next layer combines those shapes into distinct features like the loops in an 8 or upper triangle in a 4, and so on. By building a picture of these features, neural networks can determine with a very high level of accuracy the number that corresponds to a handwritten digit. Additionally, the model will learn which links between neurons are critical in making successful predictions during training. Over the course of several training cycles, and with the help of occasional manual tuning, the network will continue to learn and generate better predictions until it reaches desired accuracy.

Thus, Deep learning allows machines to solve complex problems even when using a data set that is very diverse, unstructured and inter-connected. Deep learning networks excel at dealing with vast amount of disparate data. In fact, the larger the amount of data the more efficient Deep learning becomes and the more deep learning algorithms learn, the better they perform.

Few additional links on this topic:
MIT Technology Review: https://www.technologyreview.com/s/513696/deep-learning/
Cambridge Univerisity paper: https://bit.ly/2Fbbrlr