If Artificial Intelligence (AI) makes you think of a robot takeover movie, you might think of AI as a future technology. But it’s actually used in many areas of your life right now. In this backgrounder, we will explore some of the tools that AI has made possible. But before you go farther, you need to know what Machine learning (ML) is. If you have not already read the Machine learning Backgrounder, you will want to do it now. Most of the applications (apps) we will discuss involve machine learning.
Natural Language Processing
Have you ever used a search engine? Or used the autocorrect feature to catch your spelling mistakes? If so, you used an app that involved Natural Language Processing (NLP). Natural language is the speech and text we humans use to communicate with each other.
But humans and computers do not speak the same language. This is one of the biggest problems in human-computer communication. NLP tries to solve this problem. As people, we use text and voice to communicate. We call this unstructured data. Computers only understand structured data. Structured data is information stored in spreadsheets and databases. A database is a fancy type of spreadsheet that is organized in a way for computers to understand. Structured data contains information with patterns, such as telephone numbers or email addresses. Unstructured data contains information without patterns, such as text messages and images. What NLP does is turn our unstructured data into structured data that can be used by computers.
Image - Text Version
You could imagine structured data looking like a group of squares in rows and columns. You could imagine unstructured data looking like a group of squares that are randomly placed.
Did you know?
About 80% of our digital data is unstructured data.
How is this useful? Let’s consider some real life examples.
Chatbots are one of the many apps that rely on NLP. The word "chatbot" comes from the words "chat" and "robot". But there are no robots involved with this technology. Chatbots are software programs.
Chatbots are an example of an app you can find on the web. Many companies use chatbots for customer service. You may see them pop up when you go to a website. Chatbots help people get to the right service by answering questions. This means that they must be able to understand the question and give the best possible answer. To do both, the chatbot relies on information stored in a database. If what the customer has typed is not in the database, then the chatbot cannot do its job. This is where machine learning can come in.
Machine learning can help chatbots understand different ways of saying the same thing. That may sound easy to you, but it is tricky for a computer. It would be like someone asking you a question in a language you don't understand. Machine learning teaches the chatbots, like you would learn a new language. It is this kind of learning that would tell a computer that OK, K, okay and a thumbs up emoji all mean that same thing.
NLP can even help companies figure out how customers are feeling. For example, if a person used words associated with anger, a chatbot could connect them directly to a human!
NLP is an essential tool for web searches and recommendation engines. Web search tools try to find the most relevant information based on what you are looking for. To do this, they need to understand the different web pages they can suggest. This involves analyzing text in news articles, blogs, and even the language in videos. By looking for the use of specific words and phrases, NLP helps search engines find you what you want.
NLP is also useful for email spam filters. NLP can help computers better understand what emails mean. This can make them better at catching and redirecting fraudulent emails.
NLP can also be useful in other areas, such as science and business. Scientific research is usually shared in scientific papers for people to read. These papers are often very long and very technical, making them hard to read. NLP could summarize each paper for the scientist. That would make it easier for scientists to find and read only what they need.
In business, law firms have been using NLP for years. Like scientific papers, legal documents can be long and complicated. The good news is that these documents are usually written using standard formats. That lets NLP find and sort data for users. Computers can find information like dates, who is involved, and the results of court cases.
Speech recognition (SR) also uses NLP. It involves turning audio language into text. A simple example of this would be talking to a chatbot on the phone. Web search tools use speech recognition to understand videos.
NLP can only understand a person's words. More complex systems also use other information from speech, such as tone. A system that analyzes a person's tone of voice can identify if they sound angry, sad or happy. Combining NLP and speech recognition gets us much closer to having computers understand people.
NLP and Language Barriers
NLP has allowed new breakthroughs in the world of multilingual communications as well. Automatic translators on the web are now tools that everyone can use. Together with speech recognition, NLP can let people speaking different languages communicate. You can now download many free apps for this on smartphones. These apps allow people on the street, at school or in the workplace to communicate. It can also help families, especially grandparents. They might not be fluent in the same language as their grandchildren. It is also very useful when travelling to countries that do not speak your language.
NLP also breaks down language barriers for people with disabilities. Hearing-impaired people can have easier access to closed captioning of any content. But even better, AI apps now exist to support them in their daily lives and allow them to “see” sounds. Because of the face masks used during the COVID outbreak, it is now impossible to lip read. These same apps can now help them.
Combine this technology with computer vision and get a system that can turn sign language into speech!
Smart Virtual Assistants
The most popular speech recognition apps are virtual assistants. Apple’s Siri, Microsoft’s Cortana, Amazon’s Alexa and Google’s Google are examples of virtual assistants. Virtual assistants are a sophisticated kind of chatbot. They have much better NLP and speech recognition skills. Virtual assistants can also do different types of tasks. They can play music, find a document or look up a location on a map.
Did you know?
Early virtual assistants had female voices. Based on feedback from users, some virtual assistants now offer voices of different genders. But the best solution might be a gender-neutral voice, such as that of Q, the virtual assistant. What do you think of this voice? Listen to it in the video below.
Having your own personal assistant sounds pretty useful, but it comes with a price. When you allow technology to be accessible at all times, it needs to be listening in at all times. The risk can be reduced by adjusting a few settings. Be smart with your smart devices and what you say and do around them!
What the Future Might Bring
NLP is a technology that is moving very fast. And more companies are finding ways to use it. Health care is one area in which NLP can be of a lot of help. NLP can help save doctors time by asking patients basic questions before they see the doctor. Tools like this could be very useful in remote areas where people do not always have access to doctors.
Robots are beginning to be used to care for people, such as the elderly. NLP could help these robots to better understand them. NLP is also a useful tool that could assess someone's mental health. It could be used on helplines to help identify high risk cases.
So the next time you search for something online or talk to a chatbot, remember that it could not happen without AI and ML.