DISTRIBUTED HIERARCHICAL TEXT CLASSIFICATION FRAMEWORK

• US 20080126280A1
• Filed: 08/15/2006
• Published: 05/29/2008
• Est. Priority Date: 06/26/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Liu, Tie-Yan, Zeng, Hua-Jun
• Granted Patent: US 7,809,723 B2
• Time in Patent Office: Days
• US Class Current: 706/20
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]

Abstract

A method and system for distributed training of a hierarchical classifier for classifying documents using a classification hierarchy is provided. A training system provides training data that includes the documents and classifications of the documents within the classification hierarchy. The training system distributes the training of the classifiers of the hierarchical classifier to various agents so that the classifiers can be trained in parallel. For each classifier, the training system identifies an agent that is to train the classifier. Each agent then trains its classifiers.

Claims

1. A method for training a hierarchical classifier for classification of documents into a classification hierarchy, the method comprising:

providing training data for training the classifiers, the training data including documents and classifications of the documents within the classification hierarchy;

for each classifier for a classification within the classification hierarchy,

identifying one of a plurality of agents to train the classifier so that multiple agents train different classifiers; and

under control of the identified agent, training the classifier

wherein the classifiers trained by the multiple agents form the hierarchical classifier.

2. The method of claim 1 wherein each agent executes on a distinct computing device.

3. The method of claim 1 wherein each classifier is a binary classifier for a classification that classifies documents within that classification as being within or not within one sub-classification.

5. The method of claim 1 wherein the classifiers are binary classifiers and the training of a classifier uses a cross validation technique to determine a confidence threshold for being within a classification.

6. The method of claim 5 including selecting a confidence threshold based on a middle of a largest interval with a maximum F1 score.

7. The method of claim 1 wherein the identifying of agents includes:

assigning a classifier to each agent; and

assigning unassigned classifiers to agents based on complexities of training the unassigned classifiers and complexities of training classifiers assigned to each agent.

8. The method of claim 7 wherein the complexity of training a classifier is based on the number of documents in the training data times the number of classifications.

9. The method of claims 8 wherein the number of classifications for a binary classifier is two.

10. The method of claim 7 wherein an unassigned classifier with the highest complexity is assigned to an agent that has been assigned classifiers with the smallest total complexity.

11. The method of claim 1 wherein a controller identifies agents to train the classifiers and notifies the identified agents.

4. The method of claim 4 wherein the training is performed with a support vector machine.

12. A computer system for training a hierarchical classifier for classification into a classification hierarchy, comprising:

a training data store having training data for training classifiers of the hierarchical classifier, the training data including documents and classifications of the documents within the classification hierarchy;

a controller that, for each classifier of a classification within the classification hierarchy, identifies one of a plurality of agents to train the classifier and notifies the identified agent to train the classifier; and

a plurality of agents executing on different computer devices that receive notifications to train classifiers and train the classifiers using the training data

wherein the classifiers trained by the multiple agents form the hierarchical classifier.

13. The computer system of claim 12 wherein a classifier is a binary classifier for a classification that classifies documents within that classification as being within or not within a sub-classification.

14. The computer system of claim 12 wherein the classifiers are binary classifiers and the training of a classifier uses a multi-fold cross validation technique to determine a confidence threshold for being within a classification.

15. The computer system of claim 14 wherein the confidence threshold is based on a middle point of a largest interval with a maximum F1 score.

16. The computer system of claim 12 wherein the controller identifies agents by assigning a classifier to each agent and then assigning unassigned classifiers to agents based on complexities of training the unassigned classifiers and complexities of training classifiers already assigned to each agent.

17. The computer system of claim 16 wherein the complexity of training a classifier is based on the number of documents in the training data and the number of classifications.

18. The computer system of claim 17 wherein an unassigned classifier with the highest complexity is assigned to an agent that has been assigned classifiers with the smallest total complexity.

19. A computer-readable medium containing instructions for controlling a computer to train a hierarchical classifier for classification into classification hierarchy, by a method comprising:

for each classifier of a classification within the classification hierarchy,

identifying one of a plurality of agents to train the classifier based on complexities of training classifiers assigned to the agent and complexity of training the classifier; and

notifying the identified agent to train the classifier using training data that includes documents and classifications.

20. The computer-readable medium of claim 19 wherein features for use in training each classifier are automatically selected based on analysis of training data.