Table narration using narration templates

• US 10,318,626 B2
• Filed: 08/25/2014
• Issued: 06/11/2019
• Est. Priority Date: 05/13/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Guggilla, Chinnappa, Mungi, Ashish, Narayanan, Purushothaman K., Parikh, Ankur S., Singla, Krishma, Thomas, Bijo A.
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Villena, Mark
• Application Number:
  US14/467,177
• Publication Number:
  US 20150331846A1
• Time in Patent Office: 1,751 Days
• CPC Class Codes: G06F 16/9017 using directory or table look-up use of a directory or look-up table in file systems G06F16/13
• CPC Class Codes: G06F 40/18 of spreadsheets form-filling G06F40/174
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/221 Parsing markup language streams streaming G06F40/149
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may include parsing the extracted table. The method may also include performing structural analysis on the parsed extracted table. The method may further include selecting at least one structural template based on the structural analysis of the parsed extracted table. Additionally, the method may include selecting the at least one narration template based on the at least one selected structural template. The method may also include applying the at least one selected narration template to the extracted table. The method may further include narrating the extracted table based on the applying of the at least one selected narration template to the extracted table.

Claims

1. A method for narrating a table using at least one narration template, wherein the table is extracted from a data source, the method comprising:

parsing, by a computing device, the extracted table;

performing, by the computing device, structural analysis on the parsed extracted table, wherein performing the structural analysis comprises determining a table layout and schema associated with the extracted table, and wherein determining the table layout comprises determining a number of rows, a number of columns, a number of headers, a number of sub-headers, a number of categories and a size and a span associated each of the determined number of rows, the determined number of columns, the determined number of headers, the determined number of sub-headers, and the number of categories;

selecting, by the computing device, at least one structural template associated with a plurality of stored structural templates based on the structural analysis of the parsed extracted table, wherein the selected at least one structural template is associated with the determined table layout and schema;

selecting, by the computing device, the at least one narration template associated with a plurality of stored narration templates based on the at least one selected structural template;

applying, by the computing device, the at least one selected narration template to the extracted table, wherein applying the at least one selected narration template to the extracted table comprises applying a plurality of narration formulas specified in the selected narration template, and wherein the plurality of narration formulas comprise a plurality of natural language words, phrases, and sentences that is static as specified within a narration formula or dynamic based on a plurality of content associated with the extracted table, and wherein the plurality of narration formulas continue to be created, updated, and maintained separately, in a repository on a server;

resolving, by the computing device, a plurality of variables associated with the extracted table, wherein the resolving comprises comparing at least one row of the extracted table with at least one other row of the extracted table;

narrating, by the computing device, the extracted table based on the applying of the at least one selected narration template to the extracted table and based on the resolving of the plurality of variables associated with the extracted table; and

displaying, by the computing device, a narrative output, the narrative output being a natural language output, based on a horizontal narration with comparison of the at least one row of the extracted table with the at least one other row of the extracted table, wherein the displayed narrative output comprises displaying a first table narration output of the at least one row as compared to a displayed second narration output of the at least one other row.

2. The method of claim 1, wherein the at least one selected structural template comprises at least one key element of the table structure that is necessary to determine the at least one selected narration template.

3. The method of claim 1, wherein the at least one selected narration template is based on a mapping of the at least one selected structural template to the at least one selected narration template.

4. The method of claim 3, wherein the mapping is based on at least one key element required to map the least one selected structural template to the at least one selected narration template.

5. The method of claim 1, wherein the at least one selected structural template is based on a mapping of the at least one selected narration template to the at least one selected structural template.

6. The method of claim 5, wherein the mapping is based on at least one key element required to map the at least one selected narration template to the at least one selected structural template.

7. The method of claim 1, wherein the at least one selected narration template comprises at least one key element for defining the at least one selected narration template.

8. The method of claim 7, wherein the at least one key element comprises at least one of an natural language processing (NLP) element and a narration formula.