Other

International Business Machines Corporation

Zheng Yu

Feng Cao

Boliang Chen

Qicheng Le

Xinguo Yu

Embedding representation for a document is generated based on clustering words in the document. Representative clusters are selected and a weighted sum of the embeddings of the words in the selected clusters is determined as a document embedding. Documents are labeled based on document embeddings. A machine learning algorithm is trained using the documents. The machine learning algorithm predicts a label of a given document based on the given document's document embedding.

Event clustering and classification with document embedding

A scissor type hammer mill, mainly includes an inlet (), hammers (), a rotor (), a screen () and a screen carriage () thereof, an outlet (), a hammermill body (), and a motor (), and further includes a stationary hammer frame () and stationary hammer blades () provided on the stationary hammer frame (). The stationary hammer frame is fixed on the hammermill body, and the stationary hammer blades are fixed on the stationary hammer frame, the stationary hammer blades are mounted in parallel to a rotation plane of the hammers with a distance therebetween. When the material enters into the cavity of the hammer mill, the material form a rotating material ring after being hit by the hammers, and the material is milled once again after the material ring hits the stationary hammer blade. Meanwhile, the stationary hammer blades lower the rotation speed of the material ring and change the moving direction of the material, and a component force for the movement of material towards a normal direction of the screen apertures is increased, which facilitates improving the milling efficiency, and improve the uniformity of the material to be milled.

Growing community of inventors

Shanghai, China

Zheng Yu