Method and apparatus for summarizing one or more text messages using indicative summaries

• US 20050262214A1
• Filed: 04/27/2004
• Published: 11/24/2005
• Est. Priority Date: 04/27/2004
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Bagga, Amit, Nenkova, Ani N.
• Granted Patent: US 8,868,670 B2
• Time in Patent Office: Days
• US Class Current: 709/207
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

A method and apparatus are provided for summarizing a text message, such as an email message or a transcribed audio message. A portion of each text message, such as a sentence, is extracted as an indicative summary of the text message based on a degree of overlap of words in the sentence with a set of words, such as words in the message subject or words in a related root message. The extracted portion is based on a score for each portion of the text message, such as a sentence. An interface is also provided for presenting the indicative summaries of a set of related text messages to a user.

Claims

1. A method for summarizing a text message, comprising:

extracting a portion of said text message as an indicative summary of said text message based on a degree of overlap of words in said portion with a set of words.

2. The method of claim 1, wherein said set of words is a set of words in a subject associated with said text message.

3. The method of claim 1, wherein said set of words is a set of words in a root message associated with said text message.

4. The method of claim 1, wherein said portion is a sentence.

5. The method of claim 1, further comprising the step of extracting a portion of said text message for each of a plurality of text messages in a thread.

6. The method of claim 5, further comprising the step of displaying said extracted portions of said text message for each of a plurality of text messages in a thread.

7. The method of claim 1, wherein said extracting step further comprises the step of determining whether said text message is a root message or a follow-up message.

8. The method of claim 7, wherein said extracting step further comprises the step of computing a score for each sentence of a root message based on an overlap between certain word types in each sentence in said root message and a subject of said root message.

9. The method of claim 7, wherein said certain word types comprise noninflected forms of verbs, nouns, adjectives and adverbs in said root message.

10. The method of claim 7, wherein said extracting step further comprises the step of computing a score for each sentence of a follow-up message based on an overlap between certain word types in each sentence in said follow-up message and said root message.

11. The method of claim 7, wherein said certain word types comprise verbs and nouns.

12. The method of claim 1, wherein said text message is a transcribed audio message.

13. An apparatus for summarizing a text message, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

extract a portion of said text message as an indicative summary of said text message based on a degree of overlap of words in said portion with a set of words.

14. The apparatus of claim 13, wherein said set of words is a set of words in a subject associated with said text message.

15. The apparatus of claim 13, wherein said set of words is a set of words in a root message associated with said text message.

16. The apparatus of claim 13, wherein said portion is a sentence.

17. The apparatus of claim 13, wherein said processor is further configured to extract a portion of said text message for each of a plurality of text messages in a thread.

18. The apparatus of claim 17, wherein said processor is further configured to display said extracted portions of said text message for each of a plurality of text messages in a thread.

19. The apparatus of claim 13, wherein said processor is further configured to determine whether said text message is a root message or a follow-up message.

20. The apparatus of claim 13, wherein said processor is further configured to compute a score for each sentence of a root message based on an overlap between certain word types in each sentence in said root message and a subject of said root message.

21. The apparatus of claim 20, wherein said certain word types comprise noninflected forms of verbs, nouns, adjectives and adverbs in said root message.

22. The apparatus of claim 13, wherein said processor is further configured to compute a score for each sentence of a follow-up message based on an overlap between certain word types in each sentence in said follow-up message and said root message.

23. The apparatus of claim 22, wherein said certain word types comprise verbs and nouns.

24. An article of manufacture for summarizing a text message, comprising a machine readable medium containing one or more programs which when executed implement the step of:

extracting a portion of said text message as an indicative summary of said text message based on a degree of overlap of words in said portion with a set of words.

25. A method for presenting a plurality of related text messages to a user, comprising:

presenting an extracted portion of each of said plurality of related text messages as an indicative summary of said plurality of related text messages, wherein said extracted portion is based on a degree of overlap of words in said portion with a set of words.

26. The method of claim 25, wherein said displaying step provides an interface that can be accessed over a network.

27. The method of claim 25, wherein said displaying step provides an interface that can be accessed using prompts in a voice mail system.

28. The method of claim 27, wherein voice mail system converts said extracted portions to speech and presents said extracted portions in audio form.