Many　applications　today　need　to　manage　data　that　is　uncertain,　such　as　information　extraction　(IE),　data　integration,　sensor　RFID　networks,　and　scientific　experiments.　Top-k　queries　are　often　natural　and　useful　in　analyzing　uncertain　data　in　those　applications.　In　this　paper,　we　study　the　problem　of　answering　top-k　queries　in　a　probabilistic　framework　from　a　state-of-the-art　statistical　IE　model-semi-Conditional　Random　Fields　(CRFs)-in　the　setting　of　Probabilistic　Databases　that　treat　statistical　models　as　first-class　data　objects.　We　investigate　the　problem　of　ranking　the　answers　to　Probabilistic　Databases　query.　We　present　efficient　algorithm　for　finding　the　best　approximating　parameters　in　such　a　framework　to　efficiently　retrieve　the　top-k　ranked　results.　An　empirical　study　using　real　data　sets　demonstrates　the　effectiveness　of　probabilistic　top-k　queries　and　the　efficiency　of　our　method.　©　2010　ACADEMY　PUBLISHER.