Document summarizer for word processors

• US 6,349,316 B2
• Filed: 04/08/1999
• Issued: 02/19/2002
• Est. Priority Date: 03/29/1996
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Thorpe, Christopher A., Dolan, William B., Fries, Edward J., Fein, Ronald A., Messerly, John, Cokus, Shawn J.
• Primary Examiner(s): Alam, Hosain T.
• Assistant Examiner(s): Kindred, Alford W.
• Application Number:
  US09/289,085
• Publication Number:
  US 20010021938A1
• Time in Patent Office: 1,048 Days
• Field of Search: 707/6-530, 707/531, 707/532, 707/533, 364/410.1, 364/411.1
• US Class Current: 715/267
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation

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. A computer-implemented method for summarizing documents, comprising the following steps:

(a) counting how frequently content words appear in a document to produce frequency counts for corresponding content words;

(b) scoring individual sentences according to the content words contained in the sentences;

(c) identifying a sentence with the highest score;

(d) adjusting the frequency counts of the content words that appear in the highest scoring sentence to remove an influence of the highest scoring sentence; and

(e) re-scoring the sentences based on the adjusted frequency counts.

2. A computer-implemented method as recited in claim 1 further comprising the step of repeating steps (b) to (e).

3. A computer-implemented method as recited in claim 1 further comprising the step of performing a cue-phrase analysis by comparing words and phrases in the sentences with a pre-compiled list of words and phrases and setting conditions on use of sentences that contain any words or phrases on the list.

4. A computer-implemented method as recited in claim 3 further comprising the step of creating a summary which contains higher scoring sentences and which may include conditioned sentences in an event that the conditions are satisfied.

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

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

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

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