AI Technologies

Natural Language Understanding

With NLU, computers understand the structure and meaning of human language. The human interprets and communicates the intent of a sentence for the computer to read, decipher and understand in a valuable manner.

WHAT IS Natural language understanding

The what

Natural Language Understanding (NLU) is a subset of Natural Language Processing (NLP). In NLP, machines analyze large amounts of data to understand written and spoken human languages, while NLU focuses on machines understanding the actual intent or meaning behind what humans say or write.

Natural Language Understanding is an AI-hard problem – solving it would mean a machine doesn’t just take in information – it comprehends and responds just like a human would.

WHY DO YOU NEED Natural language understanding

The why

A vast amount of human-generated data is unstructured natural language – social media content, customer reviews, and academic papers to name a few. Reading, categorizing, and extracting what’s actually essential information would be extremely time-consuming for a person – and people are prone to bias and human error.

NLU can process large amounts of unstructured data – taking just milliseconds per document. Imagine how long it would take a human to read hundreds of thousands of Instagram comments about your brand and categorize them by topic or by the different emotions your brand generates.

Humans and machines are collaborating more than ever, and the ability for a machine to understand the intent behind human language and extract critical pieces of information – like sentiment, dates, names, and places – is what allows human-like virtual assistants, chatbots, and phone triage systems to exist.

How Natural Language Understanding works

NLU uses algorithms that transform human language (unstructured data) into a format that machines can understand (structured data). An entity is a particularly important piece of data, and natural language understanding uses entity recognition to extract specific information like dates, times, locations, numbers, or any other words that are considered important.

NLU then analyses text to determine the meaning behind what a person says. It uses intent recognition to identify a user’s sentiment (attitude or feeling) and what they mean. NLU is designed to understand intent even with mispronunciations, grammatical mistakes, and other human errors.

How Natural Language Understanding works

in Kepler

in Kepler

Kepler doesn’t have just one strategy – it goes far beyond using the same algorithm for all cases.
Instead, it analyzes the key characteristics of your text in order to decide which strategy to follow – from the text pre-processing to the machine learning algorithm to be used.

After the pre-processing pipeline, Kepler chooses between a series of machine learning algorithms to complete the classification task.

This list of algorithms includes:

1D Convolution Neural Network with fine-tuning word embedding is ideal to extract sentiment such as angry, happy, sad terms

Recurrent Neural Network with fine-tuning the word embedding is for cases where the order of the information is really important.

BERT language model, introduced by Google in 2019, is excellent to extract contextual information while avoiding information loss.

TD-IDF and fully connected networks are optimized for small datasets

Natural Language Understanding Applications

Classifying legal
documents with Natural Language Understanding

A large law firm receives thousands of documents a day, and these documents have to be directed to the right department or archived under the right folder. A human with legal or paralegal knowledge would have to do this task, which would be a waste of resources and result in delays caused by a large queue of documents – not to mention the risk of human error. Using NLU, AI tools can separate and classify texts and separate them into 45 different classes – saving a lot of time and allowing employees to focus on more important work.

Analyzing customer sentiment with Natural Language Understanding

A company is launching a new product in the next few months. The company wants to be able to better plan the production, distribution, and marketing of its product, so it’s planning to launch a series of marketing campaigns to measure sentiment around the product and determine its potential market share per geography. Analyzing all the information would be extremely time-consuming for a person and costly for the company. NLU is able to classify social media comments according to the sentiment generated – positive, negative, or neutral – much faster than any human, and saves a lot of time and money.

Routing customers to the
right service department
with Natural Language Understanding

A customer contacts a company on their website, Based on the content of the message, NLU is able to automatically process the request, identifying the relevant department, and route the message to the correct representative. Going one step further, the algorithm can decode the meaning behind the words, choosing a relevant response, or providing context to the operator, based on the customers intent.

Want to upskill your AI? We’ve got you:

In addition to platform training, our onboarding experience helps you build a foundation that helps you achieve success from Day 1:

AI primer on key data science terms and processes

Applied AI training on how to run a successful AI project

AI roadmap advice

How to pilot AI use cases

We also offer in-depth services related to data strategy and transformation, system integration and more.

Tap into the power of AI

With Kepler, it’s easy to answer complex questions using the power of machine learning and deep learning.

This site is registered on as a development site.