It　is　increasing　important　to　identify　automatically　thematic　structures　from　massive　scientific　literature.　The　interdisciplinarity　enables　thematic　structures　without　natural　boundaries.　In　this　work,　the　identification　of　thematic　structures　is　regarded　as　an　overlapping　community　detection　problem　from　the　citation-link　network.　Thus,　the　overlapping　thematic　structures　can　be　detected　from　citation-link　network　with　a　mixed-membership　stochastic　blockmodel,　armed　with　stochastic　infer　algorithm.　Experimental　results　on　the　astro　dataset　indicate　that　it　is　feasible　to　extract　overlapping　thematic　structures.