Abstract: Disclosed is a method and an apparatus NER-orientated Chinese clinical text data augmentation, and unannotated data and annotated data of label linearization processing through data preprocessing. A concealed part is predicted based on retained information by using the unannotated data and concealing part of information in text, and meanwhile an entity word-level discrimination task is introduced for pre-training of a span-based language model; and a plurality of decoding mechanisms are introduced in a fine-tune stage, a relationship between a text vector and text data is obtained based on the pre-trained span-based language model, linearized data with entity labels is converted into the text vector, and text generation is performed through forward decoding and reverse decoding in a prediction stage of a text generation model to obtain enhanced data with annotation information.

Abstract: An oral capsule formulation of a PARP inhibitor and a preparation method. The oral capsule formulation comprises a solid dispersion powder of an active ingredient 5-fluoro-1-(4-fluoro-3-(4-(pyrimidin-2-yl)piperazine-1-carbonyl)benzyl)quinazoline-2,4(1H,3H)-dione, a filler, a disintegrant, a glidant, and a lubricant, wherein less than 10 wt. % of the active ingredient in the solid dispersion powder is in a crystalline form. The defects of the fluidity, hygroscopicity and cohesiveness of the solid dispersion powder which result in the difficulty of production scale up of capsule formulation are addressed, and thus commercial scale production can be achieved, and the prepared capsule exhibits proper dissolution rate, excellent storage stability, meanwhile with a reasonable production cost.