Communications of the ACM
Why Machine Learning Can't Understand Human Language
All deep learning-based language models start to break as soon as you ask them a sequence of trivial but related questions because their parameters can't capture the unbounded complexity of everyday life.
In recent years, researchers have shown that adding parameters to neural networks improves their performance on language tasks. However, the fundamental problem of understanding language remains unsolved. And this is because the AI community has abandoned knowledge-based systems, argue Marjorie McShane and Sergei Nirenburg in their new book, Linguistics for the Age of AI.
In an interview, McShane contends that machine learning must overcome several barriers, first among them being the absence of meaning.
From TechTalks
View Full Article
No entries found