Extracting attributes from embedded table structures
Embodiments include methods, system and computer program products for extracting attributes from embedded table structures in a document. Aspects include identifying a table in the document and identifying one or more headers of the table by locating co-occurring attributes in the table. Aspects also include identifying a plurality of values in the table and creating an annotation for each of the plurality of values value in the table, wherein each annotation includes text extracted from the one or more headers that correspond to the location of the value in the table.
1. A method of extracting attributes from embedded table structures in a document, the method comprising:
determining a type of the document;
obtaining attributes from a cartridge that includes specific domain data elements of interest, wherein the cartridge is selected upon the type of the document and wherein the attributes include specific domain data elements of interest for the type of document;
identifying a table in the document;
identifying one or more candidate headers of the table by analyzing a font styling;
identifying one or more headers from the one or more candidate headers based on a determination that a concentration of attributes in one or more candidate headers exceeds a threshold value;
classifying the one or more headers as a primary header primary based on a determination that a numerical value is present in a corresponding row/column of the one or more headers;
classifying the one or more headers as a qualifying header based on a determination that a numerical value is not present in the corresponding row/column of the one or more headers;
identifying a plurality of values in the table; and
creating an annotation for each of the plurality of values value in the table, wherein each annotation includes text extracted from the one or more headers that correspond to the location of the value in the table.
2. The method of claim 1 , wherein the type of document includes one of a medical document, an insurance document, and a financial document.
3. The method of claim 1 , wherein the one or more headers of the table are identified as at least one column header and at least one row header and wherein the plurality of values in the table are located in between the at least one column header and the at least one row header.
4. A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
determining a type of the document;
obtaining attributes from a cartridge that includes specific domain data elements of interest, wherein the cartridge is selected upon the type of the document and wherein the attributes include specific domain data elements of interest for the type of document;
identifying a table in the document;
identifying one or more headers of the table by analyzing a font styling;
identifying one or more headers from the one or more candidate headers based on a determination that a concentration of attributes in one or more candidate headers exceeds a threshold value;
classifying the one or more headers as a primary header primary based on a determination that a numerical value is present in a corresponding row/column of the one or more headers;
classifying the one or more headers as a qualifying header based on a determination that a numerical value is not present in the corresponding row/column of the one or more headers;
identifying a plurality of values in the table; and
creating an annotation for each of the plurality of values value in the table, wherein each annotation includes text extracted from the one or more headers that correspond to the location of the value in the table.
5. The system of claim 4 , wherein the type of document includes one of a medical document, an insurance document, and a financial document.
6. The system of claim 4 , wherein the one or more headers of the table are identified as at least one column header and at least one row header and wherein the plurality of values in the table are located in between the at least one column header and the at least one row header.
7. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer processor to cause the computer processor to perform a method comprising:
determining a type of the document;
obtaining attributes from a cartridge that includes specific domain data elements of interest, wherein the cartridge is selected upon the type of the document and wherein the attributes include specific domain data elements of interest for the type of document;
identifying a table in the document;
identifying one or more headers of the table by analyzing a font styling;
identifying one or more headers from the one or more candidate headers based on a determination that a concentration of attributes in one or more candidate headers exceeds a threshold value;
classifying the one or more headers as a primary header primary based on a determination that a numerical value is present in a corresponding row/column of the one or more headers;
classifying the one or more headers as a qualifying header based on a determination that a numerical value is not present in the corresponding row/column of the one or more headers;
identifying a plurality of values in the table; and
creating an annotation for each of the plurality of values value in the table, wherein each annotation includes text extracted from the one or more headers that correspond to the location of the value in the table.
8. The computer program product of claim 7 , wherein the type of document includes one of a medical document, an insurance document, and a financial document.
9. The computer program product of claim 7 , wherein the one or more headers of the table are identified as at least one column header and at least one row header and wherein the plurality of values in the table are located in between the at least one column header and the at least one row header.