Method and apparatus for classification of relative position of one or more text messages in an email thread

• US 20060031304A1
• Filed: 04/27/2004
• Published: 02/09/2006
• Est. Priority Date: 04/27/2004
• Status: Abandoned Application

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Incorporated
• Inventors: Bagga, Amit, Nenkova, Ani N.
• Application Number:
  US10/833,262
• Publication Number:
  US 20060031304A1
• Time in Patent Office: Days
• US Class Current: 709/206
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

Methods and apparatus are disclosed for classifying the relative position of one or more text messages (including transcribed audio messages) in a related thread of text messages. One or more classifiers are applied to the text messages; and a classification of the text messages is obtained that indicates the relative position of the text messages in the thread. For example, a thread can include a root message, a leaf message and one or more inner messages, and the classification can indicate whether each text message is a root message, a leaf message or an inner message. The classifiers are trained on a set of training messages that have been previously classified to indicate a relative position of each training message in a corresponding thread. The classifiers employ one or more features that help to distinguish between root and non-root messages.

Claims

1. A method for classifying one or more text messages in a related thread of text messages, comprising:

applying one or more classifiers to said one or more text messages; and

obtaining a classification of said one or more text messages indicating a relative position of said one or more text messages in said thread.

2. The method of claim 1, wherein said thread includes a root message, a leaf message and one or more inner messages, and wherein said classification indicates whether said one or more text messages is a root message, a leaf message or an inner message.

3. The method of claim 1, further comprising the step of determining if one or more text messages said requires a response.

4. The method of claim 1, wherein said one or more classifiers are trained on a set of training messages that have been previously classified to indicate a relative position of said one or more training messages in a corresponding thread.

5. The method of claim 1, wherein said one or more classifiers includes a Naive Bayes classifier.

6. The method of claim 1, wherein said one or more classifiers includes a support vector machine classifier.

7. The method of claim 1, wherein said one or more classifiers employ a feature based on a number of non-inflected words in said one or more text messages.

8. The method of claim 1, wherein said one or more classifiers employ a feature based on a number of noun phrases in said one or more text messages.

9. The method of claim 1, wherein said one or more classifiers employ a feature based on a number of verb phrases in said one or more text messages.

10. The method of claim 1, wherein said one or more classifiers employ a feature based on a number of predefined punctuation marks in said one or more text messages.

11. The method of claim 1, wherein said one or more classifiers employ a feature based on a length of said one or more text messages.

12. The method of claim 1, wherein said one or more classifiers employ one or more dictionaries indicating whether a set of words typically occur in non-root messages or in root messages.

13. The method of claim 1, wherein at least one of said one or more text messages is transcribed from audio information.

14. An apparatus for classifying one or more text messages in a related thread of text messages, comprising:

a memory; and

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

apply one or more classifiers to said one or more text messages; and

obtain a classification of said one or more text messages indicating a relative position of said one or more text messages in said thread.

15. The apparatus of claim 14, wherein said thread includes a root message, a leaf message and one or more inner messages, and wherein said classification indicates whether said one or more text messages is a root message, a leaf message or an inner message.

16. The apparatus of claim 14, wherein said processor is further configured to determine if one or more text messages said requires a response.

17. The apparatus of claim 14, wherein said one or more classifiers are trained on a set of training messages that have been previously classified to indicate a relative position of said one or more training messages in a corresponding thread.

18. The apparatus of claim 14, wherein said one or more classifiers includes a Naive Bayes classifier.

19. The apparatus of claim 14, wherein said one or more classifiers includes a support vector machine classifier.

20. The apparatus of claim 14, wherein said one or more classifiers employ a feature based on a number of non-inflected words in said one or more text messages.

21. The apparatus of claim 14, wherein said one or more classifiers employ a feature based on a number of noun phrases in said one or more text messages.

22. The apparatus of claim 14, wherein said one or more classifiers employ a feature based on a number of verb phrases in said one or more text messages.

23. The apparatus of claim 14, wherein said one or more classifiers employ a feature based on a number of predefined punctuation marks in said one or more text messages.

24. The apparatus of claim 14, wherein said one or more classifiers employ a feature based on a length of said one or more text messages.

25. The apparatus of claim 14, wherein said one or more classifiers employ one or more dictionaries indicating whether a set of words typically occur in non-root messages or in root messages.

26. An article of manufacture for classifying one or more text messages in a related thread of text messages, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

applying one or more classifiers to said one or more text messages; and

obtaining a classification of said one or more text messages indicating a relative position of said one or more text messages in said thread.

27. The article of manufacture of claim 26, wherein said thread includes a root message, a leaf message and one or more inner messages, and wherein said classification indicates whether said one or more text messages is a root message, a leaf message or an inner message.