Systems and methods for displaying interactive topic-based text summaries

• US 7,117,437 B2
• Filed: 12/16/2002
• Issued: 10/03/2006
• Est. Priority Date: 12/16/2002
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Chen, Francine R., Zaenen, Annie E., Brants, Thorsten H.
• Primary Examiner(s): Hong, Stephen
• Assistant Examiner(s): PATEL, MANGLESH M
• Application Number:
  US10/319,545
• Publication Number:
  US 20040117740A1
• Time in Patent Office: 1,387 Days
• Field of Search: 715/530, 715/903, 715/531, 715/501.1, 704/9, 704/257, 707/3, 707/100
• US Class Current: 715/254
• CPC Class Codes: G06F 16/345 Summarisation for human users

Abstract

Techniques for displaying interactive topic-based summarization are provided. A text to be summarized is segmented. Discrete keyword, key-phrase, n-gram, sentence and other sentence constituent based summaries are generated based on statistical measures for each text segment. Interactive topic-based summaries are displayed with human sensible omitted text indicators such as alternate colors, fonts, sounds, tactile elements or other human sensible display characteristics useful in indicating omitted text. Individual and/or combinations of discrete keyword, key-phrase, n-gram, sentence, noun phrase and sentence constituent based summaries are dynamically displayed to provide an overview of topic and subtopic development within a text. A hierarchical and interactive display of texts based on the use of discrete sentence constituent based summaries which associates expansible and contractible displayed text to provide contextualized access to an interactive topic-based text summary and to an original text.

Claims

1. A method of displaying interactive topic-based text summaries comprising the steps of:

dynamically determining a text to summarize;

recursively segmenting the text into at least one segment;

dynamically determining at least one portion of the determined text to summarize;

dynamically determining at least one sentence constituent based summary type;

dynamically determining at least one sentence constituent based topic-based text summary based on selections of segments, the summary type and a statistical measure of text segment characterization and text segment differentiation; and

dynamically displaying a discrete sentence constituent based topic-based text summary based on the at least one portion of the determined text and the at least one determined sentence constituent based summary type.

2. The method of claim 1, further comprising the step of:

displaying at least one omitted text indicator associated with text omitted from the sentence constituent based topic-based text summary.

3. The method of claim 2, wherein the at least one omitted text indicator is a human sensible display characteristic.

4. The method of claim 2, wherein the at least one omitted text indicator is selectably associated with the omitted text.

5. The method of claim 4, further comprising the step of:

dynamically selecting at least one omitted text indicator to display;

dynamically displaying an omitted text associated with the omitted text indicator.

6. The method of claim 4, wherein selecting the omitted text indicator performs at least one of, expanding the omitted text associated with the omitted text indicator, collapsing the omitted text associated with the omitted text indicator.

7. The method of claim 1, wherein dynamically determining a portion of text to summarize comprises:

selecting a segment to summarize using at least one of highlighting, a bounding box, a cursor selection, mouse selection, mouse rolling over a sensitive region, mouse click, a stylus gesture and a voice command.

8. The method of claim 1, wherein the at least one sentence constituent based interactive topic-based text summary is displayed based on at least one of bullets, indentation and text placement context cues.

19. The method of claim 1, further comprising the steps of:

associating a selectable portion of the interactive topic-based text summary with a text omitted from the sentence constituent based topic-based text summary;

selectively expanding and collapsing the omitted text display based on a selection of the portion of the interactive topic based text summary.

21. The method of claim 3, wherein the human sensible display characteristic is at least one of a visual, auditory, tactile, olfactory and taste characteristic.

22. The method of claim 21, wherein the at least one visual characteristic is at least one of a text font, color, italics, bolding and placement.

9. A system for displaying interactive topic-based text summaries comprising:

an input/output circuit for receiving, a selected sentence constituent based summary type, a selected text and a dynamically determined portion of text to summarize;

a processor that retrieves the selected text, the selected sentence constituent based summary type and the dynamically determined portion of text to summarize, from the input/output circuit;

wherein the processor recursively segments the text into at least one segment and determines and displays a discrete interactive topic-based summary for a dynamically determined portion of text based on the received sentence constituent based summary type, the determined distributions and a statistical measure of text segment characterization and text segment differentiation.

10. The system of claim 9, wherein the processor receives a dynamically determined sentence constituent summary type and a portion of text to summarize.

11. The system of claim 9, wherein at least one omitted text indicator associated with text omitted from the sentence constituent based interactive topic-based text summary.

12. The system of claim 11, wherein the at least one omitted text indicator is a human sensible display characteristic.

13. The system of claim 11, wherein the at least one omitted text indicator is selectively associated with the omitted text.

14. The system of claim 13, wherein at least one omitted text indicator is selected for display;

and an omitted text associated with the omitted text indicator is dynamically displayed.

15. The system of claim 14, wherein selection of the omitted text performs at least one of, expanding the omitted text associated with the omitted text indicator, collapsing the omitted text associated with the omitted text indicator.

16. The system of claim 10, wherein the portion of text to summarize is indicated by at least one of a bounding box, a cursor selection, as stylus gesture and a voice command.

20. The system of claim 11, wherein a selectable portion of the interactive topic-based text summary is associated with a text omitted from the sentence constituent based topic-based text summary;

and an omitted text display is selectively expanded and collapsed based on selection of the selectable portions.

23. The system of claim 12, wherein the human sensible display characteristic is at least one of a visual, auditory, tactile, olfactory and taste characteristic.

24. The system of claim 23, wherein the visual characteristic is at least one of text font, text color, text italics, text bolding and placement.

17. Computer readable storage medium comprising:

computer readable program code embodied on the computer readable storage medium, the computer readable program code usable to program a computer display interactive topic-based text summaries comprising the steps of;

dynamically determining a text to summarize;

recursively segmenting the text into at least one segment;

dynamically determining at least one portion of the determined text to summarize;

dynamically determining at least one sentence constituent based summary type;

dynamically determining at least one sentence constituent based topic-based text summary based on selections of segments, the summary type and a statistical measure of text segment characterization and text segment differentiation; and

dynamically displaying a discrete sentence constituent based topic-based text summary based on the at least one portion of the determined text and the at least one determined sentence constituent based summary type.

18. A computer readable storage medium comprising:

computer readable program code embodied on the computer readable storage medium, the computer readable program code usable to program computer display interactive topic-based text summaries comprising;

p1 instructions for dynamically determining a text to summarize;

instructions for recursively segmenting the text into at least one segment;

instructions dynamically determining at least one portion of the determined text to summarize;

instructions for dynamically determining at least one sentence constituent based summary type;

dynamically determining at least one sentence constituent based topic-based text summary based on selections of segments, the summary type and a statistical measure of text segment characterization and text segment differentiation; and

instructions dynamically displaying a discrete sentence constituent based topic-based text summary based on the at least one portion of the determined text and the at least one determined sentence constituent based summary type.