Matrix Factorization and Latent Semantic Indexing Topic a Matrix factorization matrix decomposition Latent Semantic Indexing( LSi) Term-document matrices are very large But the number of topics that people talk about is small (in some sense) Clothes, movies, politics Can we represent the term-document space by a lower dimensional latent space?Matrix Factorization and Latent Semantic Indexing 2 Topic ▪ Matrix factorization = matrix decomposition ▪ Latent Semantic Indexing (LSI) ▪ Term-document matrices are very large ▪ But the number of topics that people talk about is small (in some sense) ▪ Clothes, movies, politics, … ▪ Can we represent the term-document space by a lower dimensional latent space?