Topological Interpretations of GPT-3
–arXiv.org Artificial Intelligence
This is an experiential study of investigating a consistent method for deriving the correlation between sentence vector and semantic meaning of a sentence. We first used three state-of-the-art word/sentence embedding methods including GPT-3, Word2Vec, and Sentence-BERT, to embed plain text sentence strings into high dimensional spaces. Then we compute the pairwise distance between any possible combination of two sentence vectors in an embedding space and map them into a matrix. Based on each distance matrix, we compute the correlation of distances of a sentence vector with respect to the other sentence vectors in an embedding space. Then we compute the correlation of each pair of the distance matrices. We observed correlations of the same sentence in different embedding spaces and correlations of different sentences in the same embedding space. These observations are consistent with our hypothesis and take us to the next stage.
arXiv.org Artificial Intelligence
Aug-8-2023
- Country:
- Oceania > New Zealand (0.14)
- North America > United States
- Texas (0.14)
- Virginia (0.04)
- North Carolina > Wake County
- Raleigh (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Illinois > Cook County
- Chicago (0.04)
- Europe
- Russia (0.04)
- Ukraine
- Kyiv Oblast > Kyiv (0.14)
- Luhansk Oblast (0.04)
- Donetsk Oblast (0.04)
- Asia
- Russia (0.68)
- Afghanistan (0.05)
- Pakistan (0.04)
- Middle East
- Africa > Middle East
- Genre:
- Research Report (1.00)
- Industry:
- Law > Statutes (1.00)
- Information Technology (1.00)
- Law Enforcement & Public Safety > Crime Prevention & Enforcement (0.93)
- Health & Medicine > Health Care Providers & Services (0.93)
- Leisure & Entertainment > Games (0.67)
- Media
- Television (0.68)
- Music (0.67)
- Government
- Military (1.00)
- Regional Government
- North America Government > United States Government (1.00)
- Europe Government (1.00)
- Banking & Finance
- Technology: