Related Experiment Video
Updated: Apr 20, 2026

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
Published on: September 5, 2019
Distributional semantic models for the evaluation of disordered language
Masoud Rouhizadeh1, Emily Prud'hommeaux2, Brian Roark
1Center for Spoken Language Understanding, Oregon Health & Science University.
Researchers used language analysis to identify unusual word use in children with autism. This method accurately distinguishes autism language patterns, showing potential for diagnostic tools.
Area of Science:
- Linguistics
- Developmental Psychology
- Computational Linguistics
Background:
- Children with autism spectrum disorder (ASD) often exhibit atypical language, including unusual word choices.
- Quantifying the frequency of these unexpected words in ASD language has been challenging.
- Existing methods for analyzing language in ASD are often qualitative and time-consuming.
Purpose of the Study:
- To develop and validate an automated method for identifying unexpected words in the narrative retellings of children with autism.
- To assess the accuracy of this automated method in differentiating between children with ASD and those with typical development.
- To explore the potential of computational linguistic techniques for aiding in the diagnosis of ASD.
Main Methods:
- Utilized distributional semantic models to analyze narrative retellings from children with and without autism.
- Developed a classification system to automatically identify words considered semantically or pragmatically unexpected within the context of the retellings.
- Quantified the rate of unexpected word usage as a distinguishing feature between groups.
Main Results:
- The automated classification of unexpected words demonstrated high accuracy in distinguishing between the language of children with autism and typically developing children.
- The rate of unexpected word usage was a significant differentiator between the two groups.
- The findings suggest that computational analysis of language can reveal subtle linguistic markers associated with ASD.
Conclusions:
- Automated language analysis, specifically using distributional semantic models, can effectively identify atypical word usage in children with autism.
- This approach shows promise as an objective and efficient tool for supporting the diagnostic process in autism spectrum disorder.
- Further research can refine these techniques for broader clinical application in assessing language development in neurodevelopmental conditions.
More Related Videos
09:27Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
Published on: October 13, 2018
05:22Dissociation of the Confounding Influences of Expectancy and Integrative Difficulty Residing in Anomalous Sentences in Event-related Potential Studies
Published on: May 9, 2019
Related Concept Videos
Language and Cognition
Components of Language
Language Development
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
Higher Mental Functions of the Brain: Language
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Diagnostic and Statistical Manual of Mental Disorders (DSM)
Lateralization