Tech Terms: Natural Language Processing

In the old days, you had to know how to speak the language of computers in order to use one. The dedicated few learnt precise commands in order to get a computer to undertake a task.

Jump forward a few decades, and we have moved much further along the continuum of human-computer communication.  Computers can now understand natural human language. Whether it is spoken word, written text or an exchange of social media tweets, the ability for us to be understood by our devices is just getting started. This field of computer science is called Natural Language Processing. It is powered by Artificial Intelligence to make the leap beyond the words themselves to the intended meaning.

Ironically NLP may not be a great conversation starter at a dinner party with other humans, but it is an important concept to keep in mind. It fundamentally changes what tasks are now feasible, and this will have a big impact on how we work.

Some of the key uses of NLP are:

  1. instant translation between languages
  2. sentiment analysis – to glean public opinion on a topic
  3. writing text – Forbes magazine has been writing newspaper articles with this technology
  4. summarising text to retain the most important information
  5. text classification – for example sorting emails to determine if they are spam or not
  6. chat bots – conversational way to provide information and do daily transactions

Technologies built on this NLP are creeping into all parts of daily life. From voice assistants such as Alexa, to autotranslation of social media posts to reading content you didn’t even realise was prepared by a computer, it pops up everywhere. It not only removes barriers between computers and people, but language barriers between humans. I was recently undertaking a research project and could instantly see planning research papers from non-English speaking countries due to NLP. This allowed me to consider fresh solutions from different planning jurisdictions.

We are going to take a further look at two uses of NLP in detail – sentiment analysis and chatbots – in the next two posts, including some practical examples of how they are being deployed in smart cities and in GovTech.

The more humanity lives life over the internet, the more natural human language is theoretically available to be processed. Computers don’t understand in the same way we do but they simulate understanding by analysing and learning from every piece of information available to them. NLP is definitely a technology to watch. Here are a couple of TED talks which include applications of it:

Mapping ideas worth spreading – NLP applied to 24,000 TED Talks

What I learned from 2,000 obituaries



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s