Determining a purpose of a document

• US 9,292,601 B2
• Filed: 01/09/2008
• Issued: 03/22/2016
• Est. Priority Date: 01/09/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Proctor, Larry Lee, Strong, Hovey Raymond Jr., Tang, Renjie, Zhou, Ruoyi
• Primary Examiner(s): STORK, KYLE R
• Application Number:
  US11/971,673
• Publication Number:
  US 20090177963A1
• Time in Patent Office: 2,995 Days
• Field of Search: 715/254, 715/234, 715/243, 715/255
• US Class Current: 1/1
• CPC Class Codes: G06F 16/345 Summarisation for human users

Abstract

A method of summarizing a document includes a step of extracting one or more sections of the document. The method also includes a step of separating at least one of the one or more extracted sections into one or more subsections based at least in part on a conjunctive structure of the section, wherein each subsection comprises one or more terms. The method also includes steps of determining whether one or more terms within a designated set of terms are present within at least one of the one or more subsections and, responsive to a determination that one or more terms within the designated set of terms are present within at least one of the one or more subsections, removing the one or more terms from the one or more subsections. The method also includes a step of aggregating at least a portion of the one or more sections into a summary of the document.

Claims

1. A method for summarizing a document, comprising the steps of:

extracting one or more sections of the document;

separating at least one of the one or more extracted sections into one or more subsections based at least in part on a presence of at least one conjunction within the section, wherein each subsection comprises one or more terms;

determining whether one or more terms within a designated set of terms are present within at least one of the one or more subsections;

responsive to a determination that one or more terms within the designated set of terms are present within at least one of the one or more subsections, removing the one or more terms from the one or more subsections; and

aggregating at least a portion of the one or more subsections into a summary of the document.

2. The method of claim 1, wherein the step of aggregating comprises concatenating at least a portion of the one or more subsections.

3. The method of claim 1, wherein the step of removing one or more terms within a designated set of terms found within at least one of the one or more subsections further comprises removing a portion of the subsection following a term within a given subset of the designated set of terms.

4. The method of claim 1, wherein the step of separating at least one of the one or more extracted sections into one or more subsections comprises:

determining whether a conjunction is present within a given section; and

responsive to a determination that a conjunction is present within the given section, separating the given section into one or more subsections wherein each subsection represents a portion of the section terminated by at least one of a conjunction and a punctuation mark.

5. The method of claim 1, wherein a plurality of sections are extracted and wherein the step of aggregating at least a portion of the one or more subsections comprises the steps of:

reconstituting each of the sections by concatenating the one or more subsections into which each of the sections was separated; and

aggregating only terms present in at least a plurality of the sections to form the summary.

6. The method of claim 1, further comprising the step of generating a result set comprising the terms present in the summary and, for each term present in the summary, a total number of presences of that term in the summary.

7. The method of claim 1, wherein the summary comprises a purpose feature of the document.

8. The method of claim 7, wherein the document comprises a description of an invention and wherein the purpose feature comprises a purpose of the invention.

9. The method of claim 1, wherein the document comprises at least a portion of a patent document and wherein the step of extracting at least one section of the patent document comprises extracting at least one title section comprising at least a portion of a title of the patent document, at least one abstract section comprising at least a portion of an abstract of the patent document, and at least one claim section comprising at least a portion of at least one claim of the patent document.

10. The method of claim 9, wherein each claim section is a preamble of an independent claim.

12. The method of claim 1, further comprising the step of generating a result set comprising the terms present in the summary and, for each term present in the summary, a total number of presences of that term in the document.

13. The method of claim 12, wherein the result set is used for generation of a vector space in which dimensions correspond to vocabulary terms and projection on a dimension corresponds to the number of occurrences in the document.

14. The method of claim 1, wherein the document comprises respective descriptions of (i) a purpose and (ii) details usable for achieving the purpose, and wherein the summary represents the purpose rather than the details.

11. An article of manufacture for summarizing a document, the article comprising a non-transitory storage medium encoded with one or more software programs that, when executed by a processor, perform the steps of:

extracting one or more sections of the document;

separating at least one of the one or more extracted sections into one or more subsections based at least in part on a presence of at least one conjunction within the section, wherein each subsection comprises one or more terms;

determining whether one or more terms within a designated set of terms are present within at least one of the one or more subsections;

responsive to a determination that one or more terms within the designated set of terms are present within at least one of the one or more subsections, removing the one or more terms from the one or more subsections; and

aggregating at least a portion of the one or more sections into a summary of the document.

19. The article of claim 11, wherein the summary comprises a purpose feature of the document.

20. The article of claim 11, wherein the step of separating at least one of the one or more extracted sections into one or more subsections comprises:

determining whether a conjunction is present within a given section; and

responsive to a determination that a conjunction is present within the given section, separating the given section into one or more subsections wherein each subsection represents a portion of the section terminated by at least one of a conjunction and a punctuation mark.

21. The article of claim 11, wherein a plurality of sections are extracted and wherein the step of aggregating at least a portion of the one or more subsections comprises the steps of:

reconstituting each of the sections by aggregating the one or more subsections into which each of the sections was separated; and

aggregating only terms present in at least a plurality of the sections to form the summary.

15. An apparatus for use in summarizing a document, the apparatus comprising:

a memory; and

a processor coupled to the memory and operative to perform the operations of;

extracting one or more sections of the document;

separating at least one of the one or more extracted sections into one or more subsections based at least in part on a presence of at least one conjunction within the section, wherein each subsection comprises one or more terms;

determining whether one or more terms within a designated set of terms are present within at least one of the one or more subsections;

responsive to a determination that one or more terms within the designated set of terms are present within at least one of the one or more subsections, removing the one or more terms from the one or more subsections; and

aggregating at least a portion of the one or more subsections into a summary of the document.

16. The apparatus of claim 15, wherein the operation of separating at least one of the one or more extracted sections into one or more subsections comprises:

determining whether a conjunction is present within a given section; and

responsive to a determination that a conjunction is present within the given section, separating the given section into one or more subsections wherein each subsection represents a portion of the section terminated by at least one of a conjunction and a punctuation mark.

17. The apparatus of claim 15, wherein a plurality of sections are extracted and wherein the operation of aggregating at least a portion of the one or more subsections comprises the steps of:

reconstituting each of the sections by aggregating the one or more subsections into which each of the sections was separated; and

aggregating only terms present in at least a plurality of the sections to form the summary.

18. The apparatus of claim 15, wherein the summary comprises a purpose feature of the document.