Generating sentence variations for automatic summarization

• US 20080270119A1
• Filed: 04/30/2007
• Published: 10/30/2008
• Est. Priority Date: 04/30/2007
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Suzuki, Hisami
• Application Number:
  US11/799,286
• Publication Number:
  US 20080270119A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

A new system is hereby provided that generates automatic summaries of groups of multiple documents using multiple variations of each sentence from a selected group of representative sentences from the documents, and then selecting from the multiple variations when assembling the automatic summary. The system may generate alternative strings of text, select from among the alternative strings of text, and provide a summary of the group of documents using the strings of text selected from among the alternatives. The alternative strings of text may be generated based on each of a plurality of sentences from the group of documents. Selecting from among the alternative strings of text may be based on one or more criteria indicating the strings of text to be representative of the content of the group of documents.

Claims

1. A method, implemented at least in part by a computing device, comprising:

generating a plurality of alternative strings of text based on each sentence from a plurality of sentences from a group of documents;

selecting one or more of the alternative strings of text based on one or more criteria indicating the strings of text to be representative of the content of the group of documents; and

providing a summary of the group of documents wherein the summary comprises the one or more selected strings of text.

2. The method of claim 1, wherein generating the alternative strings of text comprises selecting fragments of the sentences from the group of documents.

3. The method of claim 1, wherein generating the alternative strings of text comprises generating new strings of text based on the sentences from the group of documents.

4. The method of claim 3, wherein generating the new strings of text comprises parsing the sentences from the group of documents and generating new strings of text that are semantically consistent with the parsed sentences.

5. The method of claim 3, wherein generating the new strings of text comprises paraphrasing the sentences from the group of documents.

6. The method of claim 1, wherein generating the alternative strings of text comprises selecting sentences from the group of documents and removing portions of the sentences based on one or more criteria indicating the portions to be peripheral to the content of the group of documents.

7. The method of claim 1, wherein at least one of the documents is not in a target language in which the summary is to be provided, wherein the method further comprises translating one or more of the documents into the target language prior to generating the alternative strings of text.

8. The method of claim 1, wherein at least one of the documents is not in a target language in which the summary is to be provided, wherein the method further comprises translating the selected strings of text into the target language prior to providing the summary.

9. The method of claim 1, wherein the one or more criteria indicating the strings of text to be representative of the content of the group of documents comprise a criterion based on where the sentences on which the strings of text are based are within the documents.

10. The method of claim 1, wherein the one or more criteria indicating the strings of text to be representative of the content of the group of documents comprise a criterion based on the kinds of words contained in the strings of text.

11. The method of claim 1, wherein the one or more criteria indicating the strings of text to be representative of the content of the group of documents comprise a criterion based on the frequency with which selected words in the strings of text appear in the group of documents.

12. The method of claim 11, wherein the criterion is further based on both the frequency of the selected words in the documents individually, and the proportion of documents in the group that contain the selected words.

13. The method of claim 1, further comprising classifying the group of documents, and omitting from the summary any strings of text from documents from the group that are indicated to be outside a class defined by the classification of the group of documents.

14. The method of claim 1, wherein the summary is provided with a word count in a pre-selected range.

15. The method of claim 1, wherein providing the summary comprises generating new sentences for the summary based on the selected strings of text.

16. A medium, readable by a computing device and comprising instructions that can be executed by the computing device which configure the computing device to:

generate a plurality of alternative candidate sentences based on each of one or more sentences from a group of documents;

select one or more of the candidate sentences that are representative of the content of the group of documents; and

provide a summary of the group of documents comprising the one or more selected candidate sentences.

17. The medium of claim 16, further comprising instructions that configure the computing device such that generating the plurality of alternative candidate sentences comprises performing syntax-based simplification of the one or more sentences from the group of documents.

18. The medium of claim 16, further comprising instructions that configure the computing device such that generating the plurality of alternative candidate sentences comprises performing logical-form-based simplification of the one or more sentences from the group of documents.

19. The medium of claim 16, further comprising instructions that configure the computing device such that generating the plurality of alternative candidate sentences comprises performing paraphrasing simplification of the one or more sentences from the group of documents.

20. A computing device comprising:

means for generating candidate sentences based on content from a group of documents;

means for selecting one or more of the candidate sentences that are representative of the content of the group of documents; and

means for providing a summary of the group of documents comprising the one or more selected candidate sentences.