← Back to context Comment by jongjong 2 days ago Interesting. Makes one think. 1 comment jongjong Reply senderista 1 day ago To be clear, LSA[1] is simply applied linear algebra, not ML. I'm sure learned embeddings outperform the simple SVD[2] used in LSA.[1] https://en.wikipedia.org/wiki/Latent_semantic_analysis[2] https://en.wikipedia.org/wiki/Singular_value_decomposition
senderista 1 day ago To be clear, LSA[1] is simply applied linear algebra, not ML. I'm sure learned embeddings outperform the simple SVD[2] used in LSA.[1] https://en.wikipedia.org/wiki/Latent_semantic_analysis[2] https://en.wikipedia.org/wiki/Singular_value_decomposition
To be clear, LSA[1] is simply applied linear algebra, not ML. I'm sure learned embeddings outperform the simple SVD[2] used in LSA.
[1] https://en.wikipedia.org/wiki/Latent_semantic_analysis
[2] https://en.wikipedia.org/wiki/Singular_value_decomposition