Converting data into natural language form

• US 9,858,270 B2
• Filed: 02/07/2017
• Issued: 01/02/2018
• Est. Priority Date: 01/13/2012
• Status: Expired due to Fees

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Bird, John J., McCoy, Doyle J.
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US15/426,717
• Publication Number:
  US 20170147566A1
• Time in Patent Office: 329 Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

Converting technical data from field oriented electronic data sources into natural language form is disclosed. An approach includes obtaining document data from an input document, wherein the document data is in a non-natural language form. The approach includes determining a data type of the document data from one of a plurality of data types defined in a detection and conversion database. The approach includes translating the document data to a natural language form based on the determined data type. The approach additionally includes outputting the translated document data in natural language form to an output data stream.

Claims

1. A method implemented in a computer infrastructure, comprising:

obtaining document data from an input document;

determining, using a translation engine, a data type of the document data out of a plurality of data types using a detection and conversion database;

selecting, based on the determined data type, appropriate conversion information records from translation data stored in the detection and conversion database;

translating, using the translation engine and the appropriate conversion information records, based on the determined data type, the document data to a natural language form;

outputting, in natural language form, the translated document data to an output data stream, wherein the plurality of data types comprises a document header data;

a document field data;

a table header data;

a table detail data; and

a signature data;

applying a first keyword translation to the document data; and

applying a second keyword translation to the translated document data after the translating the document data to the natural language form.

2. The method of claim 1, wherein the obtaining comprises obtaining, from an input data stream of the input document, the document data.

3. The method of claim 1, wherein the applying the first keyword translation to the document data occurs prior to the translating the document data to the natural language form.

4. The method of claim 1, wherein the first and second keyword translations are applied using a keyword translation database.

5. The method of claim 1, further comprising providing the output data stream to a question-answering system.

6. The method of claim 1, further comprising saving the output data stream as an output document.

7. The method of claim 1, wherein:

the document data comprises plural different portions of data; and

the determining, the translating, and the outputting are respectively performed for each respective one of the plural different portions of data.

8. The method of claim 7, wherein:

the plural different portions of data are arranged in an order in the input document; and

the output translated document data comprises translated portions of data in the same order as the input document.

9. The method of claim 7, further comprising storing metadata associated with each one of the plural different portions of data.

10. A system implemented in hardware, comprising:

a processor executing a translation engine that is configured to;

obtain document data that is in a form other than a natural language from an input document;

determine, via communication with a detection and conversion database, a data type of the document data;

translate, based on the determined data type and appropriate conversion information records selected from plural different translation data stored in the detection and conversion database, the document data to natural language; and

output, in natural language, the translated document data to an output data stream, wherein;

each record is associated with one of a plurality of data types which comprise;

a document header data;

a document field data;

a table header data;

a table detail data; and

a signature data; and

each record comprises;

data used in comparisons against the document data during the determining; and

at least one conversion rule applied to the document data during the translating.

11. The system of claim 10, wherein:

the translation engine is further operable to apply a keyword translation at least one of prior to and after the translating the document data to natural language; and

the keyword translation is a separate translation from the translating the document data to the natural language.

12. The system of claim 10, wherein the translation engine is further operable to provide the output data stream to a question-answering system, wherein the output stream includes a translation map.

13. A computer program product comprising a non-transitory computer usable tangible storage medium having readable program code embodied in the tangible storage medium, the computer program product includes at least one component configured to:

obtain portions of document data that are in a non-natural language form from a document; and

for the portions, perform the steps of;

determine, through a detection and conversion database, a data type for each portion out of a plurality of data types;

applying a first keyword translation to each portion;

translate, based on the determined data type, each portion to a natural language form, wherein the plurality of data types comprises;

a document header data;

a document field data;

a table header data;

a table detail data; and

a signature data; and

applying a second keyword translation to the translated portion after the translating each portion to the natural language form.