How computers learn languages

We Need to Talk

Article from Issue 264/2022
Author(s):

Whether through voice assistants, chatbots, or the automatic analysis of documents, rapid developments in AI are helping speech technologies make inroads. But how does AI manage to understand the subtleties of human language?

Language is the medium through which people communicate and express their thoughts. It is an ancient dream of mankind to be able to communicate with a machine (for example, just watch 2001: A Space Odyssey).

Meanwhile, science has come a bit closer to this vision. The box entitled "Sample Dialogue with LaMDA" contains a conversation with the Language Model for Dialogue Applications [1] (LaMDA) dialogue model. It was assigned the identity of a Weddell Seal in the first line. As you can see, LaMDA can give grammatically and contextually correct answers and even play with the meanings of words. But how does a computer system manage to achieve language fluency?

To understand language, the system needs to know the meaning of words. For this purpose, each word is represented by a long vector of 100 to 1,000 real numbers. This vector is known as embedding. Now, for example, because "sofa" and "couch" both refer to upholstered seating furniture for several people, their embeddings should also be similar. This means that very similar numbers should be found at the same positions of the vector. Other words such as "dive" have very different meanings, so their embeddings should be very different from the one just mentioned.

[...]

Use Express-Checkout link below to read the full article (PDF).

Buy this article as PDF

Express-Checkout as PDF
Price $2.95
(incl. VAT)

Buy Linux Magazine

SINGLE ISSUES
 
SUBSCRIPTIONS
 
TABLET & SMARTPHONE APPS
Get it on Google Play

US / Canada

Get it on Google Play

UK / Australia

Related content

  • ChatGPT Clients

    Do you think ChatGPT only works in your web browser? You can also access the global chat phenomenon from your desktop – or even from the Linux command line.

  • Machine Language

    The electronic brain behind ChatGPT from OpenAI is amazingly capable when it comes to chatting with human partners. Mike Schilli picked up an API token and has set about coding some small practical applications.

  • Simon Voice Control

    Simon is a sophisticated speech recognition tool with easy access to two powerful speech recognition engines, Julius and CMU Sphinx.

  • Programming Snapshot – Markov Chains

    Markov chains model systems that jump from state to state with predetermined probabilities, but can they help write new columns like this one after learning from previously written articles?

  • Free Software Projects

    Even hardened nerds are often over-challenged by the less than intuitive field of statistics. Besides the theory, you need to know how to use the software that converts all the theory into a practical application.

comments powered by Disqus
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters

Support Our Work

Linux Magazine content is made possible with support from readers like you. Please consider contributing when you’ve found an article to be beneficial.

Learn More

News