Document summarizer for word processors

• US 20020103836A1
• Filed: 02/11/2002
• Published: 08/01/2002
• Est. Priority Date: 04/08/1999
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Christopher A. Thorpe, Edward J. Fries, John Messerly, Ronald A. Fein, Shawn J. Cokus, William B. Dolan
• Inventors: Thorpe, Christopher A., Dolan, William B., Fries, Edward J., Fein, Ronald A., Messerly, John, Cokus, Shawn J.
• Granted Patent: US 7,051,024 B2
• Time in Patent Office: Days
• US Class Current: 715/531
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

An author-oriented document summarizer for a word processor is described. The document summarizer performs a statistical analysis to generate a list of ranked sentences for consideration in the summary. The summarizer counts how frequently content words appear in a document and produces a table correlating the content words with their corresponding frequency counts. Phrase compression techniques are used to produce more accurate counts of repeatedly used phrases. A sentence score for each sentence is derived by summing the frequency counts of the content words in a sentence and dividing that tally by the number of the content words in the sentence. The sentences are then ranked in order of their sentence scores. Concurrent with the statistical analysis, during the same pass through the document the summarizer performs a cue-phrase analysis to weed out sentences with words or phrases that have been pre-identified as potential problem phrases. The cue-phrase analysis compares sentence phrases with a pre-compiled list of words and phrases and sets conditions on whether the sentences containing them can be used in the summary. Following the cue-phrase analysis, the summarizer creates a summary containing the higher ranked sentences. The summary may also include a conditioned sentence if the conditions established for inclusion of the sentence have been satisfied. The summarizer then inserts the sentence at the beginning of the document before the start of the text.

Claims

1. In a document summarizing application executing on a processing device, a computer-implemented method comprising:

constructing a sentence-based summary of a document'"'"'s writings; and

inserting the sentence-based summary at a beginning of the document.

2. A word processing application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 1.

3. An electronic mail application stored in a storage medium which directs a computer to perform in the computer-implemented method as recited in claim 1.

4. An Internet web browser application stored in a storage medium which directs a computer to perform in the computer-implemented method as recited in claim 1.

5. A computer programmed to perform the computer-implemented method as recited in claim 1.

6. A document file formed in memory as a result of the computer -implemented method recited in claim 1.

7. In a document summarizing application executing on a processing device to construct a summary of a document, wherein the summary is in part derived from counting how frequently words appear in the document, a computer-implemented method comprising:

evaluating words in the document to identify ordered sets of words that appear repeatedly in a same order;

ranking individual sentences in the document by treating the ordered sets of words as if they were single words; and

generating the summary based at least in part on the sentence rankings.

8. A word processing application stored in a storage medium which directs a computer to perform operations of the computer-implemented method as recited in claim 7.

9. An electronic mail application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 7.

10. An Internet web browser application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 7.

11. A computer programmed to perform the computer-implemented method as recited in claim 7.

12. A document file formed in memory as a result of the computer-implemented method recited in claim 7.

14. A word processing application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 13.

15. An electronic mail application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 13.

16. An Internet web browser application stored in a storage medium which directs a computer to perform the computer-implemented method as recited in claim 13.

17. A computer programmed to perform the computer-implemented method as recited in claim 13.

13. In a document summarizing application executing on a processing device, a computer-implemented method comprising:

constructing a textual content-based summary of a document'"'"'s writings; and

inserting the textual content-based summary at a beginning of the document and on a common page with starting content of the document.

18. A document file formed in memory as a result of the computer-implemented method recited in claim 13.