Latest

natural language processing

This schematic shows how words and concepts are processed

·June 18, 2022·5 min read

Can Computers Understand Complex Words and Concepts?

Artificial intelligence can understand complex words and concepts by representing the meaning of words in a similar way that correlates with human judgments.

This shows a conversation between a human and chatbot

Featured Neuroscience

·November 8, 2021·3 min read

Want to Throw off Your Chatbot? Use Figurative Language

When chatbots are faced with human interaction containing similes and idioms, their performance falls to between 10 to 20%.

This shows the word Sarcasm written in scrabble tiles

Featured Neuroscience

·May 8, 2021·5 min read

Researchers Develop Artificial Intelligence That Can Detect Sarcasm in Social Media

A newly developed artificial intelligence algorithm can accurately detect sarcasm in comments written on social media platforms.

Featured Neuroscience Open Neuroscience Articles Psychology

·February 21, 2021·5 min read

Predicting Words’ Grammatical Properties Helps Us Read Faster

When reading, people are not only able to predict the next word, but also the words' grammatical properties. This allows us to read faster. The findings could help with the development of new neural networks focused on natural language processing.

This shows the word cloud the AI generated

Featured Neuroscience

·January 13, 2020·3 min read

Leveraging AI to give voice to the voiceless

Newly developed artificial intelligence technology could help counter hate speech directed at minorities and other voiceless groups.

Featured Neuroscience

·October 25, 2019·4 min read

What 26,000 books reveal when it comes to learning language

Machine learning finds you can take a person's language behavior and estimate the types of material they have read.

This shows a plastic mask behind binary code

Featured Neuroscience Open Neuroscience Articles Psychology

·June 13, 2019·5 min read

The whisper of schizophrenia: Machine learning finds ‘sound’ words predict psychosis

A new deep learning algorithm can predict those at risk of psychosis with 93% accuracy by examining the latent semantic content of an individual's speech.

Featured Neuroscience Open Neuroscience Articles

·June 6, 2019·3 min read

Fussy, hungry, or even in pain? Scientists create an AI tool to tell babies’ cries apart

A new deep learning algorithm, based on automatic speech recognition, is able to accurately identify features in an infant's cry and differentiate between normal versus abnormal cry signals.

This is a map of Winterfell in Game of Thrones from the HBO show graphics

Featured Neuroscience Open Neuroscience Articles

·April 18, 2019·3 min read

Why language technology can’t handle Game of Thrones (yet)

Researchers improved the performance of natural language processing technology to increase recognitionion of names associated with characters in Game of Thrones, and other literature, from 7% to 90%.

Featured Neuroscience

·March 20, 2019·7 min read

Brain-inspired AI inspires insights about the brain (and vice versa)

A new deep learning system is able to predict, with great accuracy, how different brain areas respond to specific words. The model also found concepts localized to the auditory cortex are less dependent on context.