METHODS AND SYSTEMS TO SUMMARIZE A SOURCE TEXT AS A FUNCTION OF CONTEXTUAL INFORMATION

• US 20120197630A1
• Filed: 01/28/2011
• Published: 08/02/2012
• Est. Priority Date: 01/28/2011
• Status: Abandoned Application

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: LYONS, Kenton M., ROSARIO, Barbara, PERING, Trevor, WANT, Roy
• Application Number:
  US13/015,928
• Publication Number:
  US 20120197630A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/345 Summarisation for human users

Abstract

Methods and systems to summarize a source text as a function of contextual information, including to fit a summary within a context-based allotted time. The context-based allotted time may be apportioned amongst multiple portions of the source text, such as by relevance. The context-based allotted time and/or relevance may be user-specified and/or determined, such as by look-up, rule, computation, inference, and/or machine learning. During summary presentation, one or more portions of the source text may be re-summarized, such as to adjust a level of detail. A presentation rate may be user-controllable. Where new and/or changed contextual information affects an available time to review a remaining portion of the summary, the summary presentation may be automatically adjusted, and/or one or more portions of the source text may be re-summarized based on a revised context-based allotted time.

Claims

1. A computer-implemented method, comprising:

determining a text summarization compression metric as a function of a measure of a source text and a context-based allotted time in which to fit a summary of the source text; and

summarizing the source text as a function of the compression metric.

2. The method of claim 1, further including:

determining the context-based allotted time from user-context information;

wherein the user-context information includes one or more of schedule information, computer activity information, location information, motion information, activity information, status information, proximity information, and electronic messages.

3. The method of claim 1, wherein the determining of the compression metric includes:

apportioning the context-based allotted time amongst multiple portions of the source text based on a relevance of the multiple portions of the source text; and

determining the compression metric for each of the portions of the source text as a function of the measure of the corresponding portion of the source text and the corresponding portion of the context-based allotted time;

wherein the summarizing includes summarizing each of the portions of the source text as a function of the corresponding compression metric.

4. The method of claim 1, further including:

determining a revised context-based allotted time during a presentation of the summary;

re-determining the compression metric for a portion of the source text based on the revised context-based allotted time when a remaining presentation time of the summary differs from the revised context-based allotted time; and

summarizing the portion of the source text as a function of a measure of the portion and the re-determined compression metric.

5. The method of claim 1, further including:

determining a revised context-based allotted time during a presentation of the summary; and

adjusting a presentation rate of the summary when a remaining presentation time of the summary differs from the revised context-based allotted time.

6. The method of claim 1, further including:

determining one or more of the context-based allotted time and a relevance of one or more portions of the source text from contextual information;

wherein the determining includes one or more of computing, looking-up, applying rules, inferring, and machine-based learning.

7. The method of claim 6, wherein the contextual information includes one or more of:

user-context information,

event information,

location information,

travel information,

environmental information, and

historical information.

8. A system, comprising:

a text summarization compression metric system to determine a compression metric as a function of a measure of a source text and a context-based allotted time in which to fit a summary of the source text, and to output the compression metric to a text summarization system to generate the summary as a function of the compression metric.

9. The system of claim 8, further including:

a contextual information evaluator to determine the context-based allotted time from user-context information;

wherein the user-context information includes one or more of schedule information, computer activity information, location information, motion information, and electronic messages.

10. The system of claim 8, further including:

a contextual information evaluator to apportion the context-based allotted time amongst multiple portions of the source text based on a relevance of the multiple portions of the source text;

wherein the text summarization compression metric system is configured to determine the compression metric for each of the portions of the source text as a function of the measure of the corresponding portion of the source text and the corresponding portion of the context-based allotted time.

11. The system of claim 8, wherein the compression metric system is configured to:

determine a revised context-based allotted time during a presentation of the summary; and

re-determine the compression metric for a portion of the source text based on the revised context-based allotted time when a remaining presentation time of the summary differs from the revised context-based allotted time.

12. The system of claim 8, wherein the compression metric system is configured to:

determine a revised context-based allotted time during a presentation of the summary; and

adjust a presentation rate of the summary when a remaining presentation time of the summary differs from the revised context-based allotted time.

13. The system of claim 8, further including:

a contextual information evaluator to determine one or more of the context-based allotted time and a relevance of one or more portions of the source text from contextual information;

wherein the contextual information evaluator includes one or more of a look-up table, computation system, a rule, an inference engine, and a learning system.

14. The system of claim 13, wherein the contextual information includes one or more of:

user-context information;

event information,

location information,

travel information,

environmental information, and

historical information.

15. A computer program product comprising a computer readable medium having computer program logic stored therein, wherein the computer program logic includes:

text summarization compression metric logic to cause a processor to determine a compression metric as a function of a measure of a source text and a context-based allotted time in which to fit a summary of the source text.

16. The computer program product of claim 15, further including:

contextual information evaluator logic to cause the processor to determine the context-based allotted time from user-context information;

wherein the user-context information includes one or more of schedule information, computer activity information, location information, motion information, and electronic messages.

17. The computer program product of claim 15, further including:

contextual information evaluator logic to cause the processor to apportion the context-based allotted time amongst multiple portions of the source text based on a relevance of the multiple portions of the source text;

wherein the text summarization compression metric logic includes logic to cause the processor to determine the compression metric for each of the portions of the source text as a function of the measure of the corresponding portion of the source text and the corresponding portion of the context-based allotted time.

18. The computer program product of claim 15, wherein the text summarization compression metric logic includes:

logic to cause the processor to determine a revised context-based allotted time during a presentation of the summary; and

logic to cause the processor to re-determine the compression metric for a portion of the source text based on the revised context-based allotted time when a remaining presentation time of the summary differs from the revised context-based allotted time.

19. The computer program product of claim 15, wherein the text summarization compression metric logic includes:

logic to cause the processor to determine a revised context-based allotted time during a presentation of the summary; and

logic to cause the processor to adjust a presentation rate of the summary when a remaining presentation time of the summary differs from the revised context-based allotted time.

20. The computer program product of claim 15, further including:

contextual information evaluator logic to cause the processor to determine one or more of the context-based allotted time and a relevance of one or more portions of the source text from contextual information;

wherein the contextual information evaluator logic includes one or more of a look-up table logic, computation logic, rules logic, inference logic, and learning logic.