International Business Machines Corporation

Yuan Jie Zhang

Ming Lei Zhang

Dong Chen

Yan Wu

Chao Yuan Huang

Ting Ting Zhan

Yin Xi Guo

Yu Jie Gu

A computer-implemented method, according to one embodiment, includes: receiving copies of notes that were originally recorded by participants, the notes corresponding to a source document. Note fragments in the received copies of notes are identified and one or more machine learning models are used to compare the identified note fragments to pages and paragraphs in the source document that the respective note fragments are located in. Based at least in part on the comparison, the identified note fragments are merged with a copy of the source document to form a pseudo-source document. Furthermore, the pseudo-source document is output.

Merging supplemental information with the content of source material

From an input image comprising a portion of text, the portion of text is extracted. The portion of text comprises text in a first natural language. The input image is classified into a candidate scene within a set of predefined scenes. The candidate scene is scored according to a quality measure. Using a predefined scene parameter of the scored candidate scene, the portion of text is translated. In the input image, the portion of text is replaced. with the translated portion of text.

Scene recognition based natural language translation

Tent

Growing community of inventors

Ningbo, China

Yuan Jie Zhang