Dimensionality　reduction　plays　an　important　role　in　the　data　processing　of　machine　learning　and　data　mining,　which　makes　the　processing　of　high-dimensional　data　more　efficient.　Dimensionality　reduction　can　extract　the　low-dimensional　feature　representation　of　high-dimensional　data,　and　an　effective　dimensionality　reduction　method　can　not　only　extract　most　of　the　useful　information　of　the　original　data,　but　also　realize　the　function　of　removing　useless　noise.　In　this　paper,　an　unsupervised　multilayered　variational　auto-encoder　model　is　studied　in　the　text　data,　so　that　the　high-dimensional　feature　to　the　low-dimensional　feature　becomes　efficient　and　the　low-dimensional　feature　can　retain　mainly　information　as　much　as　possible.　Low-dimensional　feature　obtained　by　different　dimensionality　reduction　methods　are　used　to　compare　with　the　dimensionality　reduction　results　of　variational　auto-encoder　(VAE).　Compared　with　other　dimensionality　reduction　methods,　the　classification　accuracy　of　VAE　on　different　data　sets　is　improved　by　at　least　0.21%　and　at　most　3.7%.