[HTML][HTML] Overlap in meaning is a stronger predictor of semantic activation in GPT-3 than in humans
J Digutsch, M Kosinski - Scientific Reports, 2023 - nature.com
Modern large language models generate texts that are virtually indistinguishable from those
written by humans and achieve near-human performance in comprehension and reasoning …
written by humans and achieve near-human performance in comprehension and reasoning …
[PDF][PDF] Predicting semantic priming in Hebrew morphology using word embeddings
I Kastner - Poster presented at AMLaP, 2020 - files.de-1.osf.io
Background Word embeddings In NLP: Vector-space representations of words based on
cooccurrences. Often assumed to represent meaning (Caucheteux and King 2020). Useful …
cooccurrences. Often assumed to represent meaning (Caucheteux and King 2020). Useful …