Many　machine　learning　methods　have　been　applied　on　Named　Entity　Recognition　(NER).　Such　methods　generally　build　on　a　large　manually-annotated　training　set.　However,　the　training　set　is　usually　limited　as　human　labeling　is　costly　and　time　consuming.　Compare　to　the　training　set,　the　unlabeled　corpus　is　usually　much　bigger　and　contains　rich　information　about　language.　In　this　paper,　a　hybrid　Deep　Neural　Network　(DNN)　is　proposed　to　take　advantage　of　the　implicit　information　embedded　in　the　un-labeled　corpus.　The　experiments　show　that　F1-score　is　improved　from　85%　to　90%　(person　name),　from　75%　to　81%　(location　name),　and　from　74%　to　78%　(organization　name),　compared　with　Conditional　Random　Fields　(CRFs).　©　2014　IEEE.