Abstract: A document processing system receives an electronic document including component documents generated from various sources in different formats. Plain text data can be extracted from the electronic document in addition to formatting and structuring information. The plain text data is segmented into sections and various entities are extracted and linked from the sections. An interactive graphical user interface (GUI) that displays content including the plain text data is formatted according to the styling information and annotated entity relationships are determined from the linked entities. The GUI enables user edits to the annotated entity relationships.

Abstract: A document processing system receives an electronic document including component documents generated from various sources in different formats. Plain text data can be extracted from the electronic document in addition to formatting and structuring information. The plain text data is segmented into sections and various entities are extracted and linked from the sections. An interactive graphical user interface (GUI) that displays content including the plain text data is formatted according to the styling information and annotated entity relationships are determined from the linked entities. The GUI enables user edits to the annotated entity relationships.

Abstract: A method for automatically extracting claim candidates from complex sentences includes providing a parse tree of a text sample to be analyzed, disassembling the parse tree into a set of basic meaning-bearing clauses, assembling clauses of the set of basic clauses into a set of complex coherent statements based on permissible syntactic structures, testing the complex statements and discarding those statements that are not coherent when considered alone, discarding those complex statements that either do not provide additional information about a subject, or are too complex, removing information from a complex statement that provides supportive details about the subject, and discarding statements that restrict their subject, so that the subject cannot be generalized encompass a broader subject.