Meta learning for question classification
First Claim
1. A method for automatically classifying a first question, the method comprising:
- receiving unlabeled data;
automatically labeling said unlabeled data to produce first labeled data using a first artificial neural network, said first artificial neural network comprising a first set of weights;
transferring said first set of weights to a second artificial neural network;
receiving second labeled data comprising a second question and a corresponding answer;
training said second artificial neural network using said second labeled data;
receiving the first question; and
associating a question category with the first question using said second artificial neural network.
1 Assignment
0 Petitions
Accused Products
Abstract
A system and a method are disclosed for automatic question classification and answering. A multipart artificial neural network (ANN) comprising a main ANN and an auxiliary ANN classifies a received question according to one of a plurality of defined categories. Unlabeled data is received from a source, such as a plurality of human volunteers. The unlabeled data comprises additional questions that might be asked of an autonomous machine such as a humanoid robot, and is used to train the auxiliary ANN in an unsupervised mode. The unsupervised training can comprise multiple auxiliary tasks that generate labeled data from the unlabeled data, thereby learning an underlying structure. Once the auxiliary ANN has trained, the weights are frozen and transferred to the main ANN. The main ANN can then be trained using labeled questions. The original question to be answered is applied to the trained main ANN, which assigns one of the defined categories. The assigned category is used to map the original question to a database that most likely contains the appropriate answer. An object and/or a property within the original question can be identified and used to formulate a query, using, for example, system query language (SQL), to search for the answer within the chosen database. The invention makes efficient use of available information, and improves training time and error rate relative to use of single part ANNs.
-
Citations
19 Claims
-
1. A method for automatically classifying a first question, the method comprising:
-
receiving unlabeled data;
automatically labeling said unlabeled data to produce first labeled data using a first artificial neural network, said first artificial neural network comprising a first set of weights;
transferring said first set of weights to a second artificial neural network;
receiving second labeled data comprising a second question and a corresponding answer;
training said second artificial neural network using said second labeled data;
receiving the first question; and
associating a question category with the first question using said second artificial neural network. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. An apparatus for automatically classifying a first question, the apparatus comprising:
-
an input module configured to;
receive unlabeled data, receive first labeled data comprising a second question and a corresponding answer, and receive the first question;
a processor module configured to;
automatically label said unlabeled data to produce second labeled data using a first artificial neural network, said first artificial neural network comprising a first set of weights, transfer said first set of weights to a second artificial neural network, train said second artificial neural network using said first labeled data, and associate a question category with the first question using said second artificial neural network. - View Dependent Claims (16)
-
-
17. An apparatus for automatically classifying a first question, the apparatus comprising:
-
means for receiving unlabeled data;
means for automatically labeling said unlabeled data to produce first labeled data using a first artificial neural network, said first artificial neural network comprising a first set of weights;
means for transferring said first set of weights to a second artificial neural network;
means for receiving second labeled data comprising a second question and a corresponding answer;
means for training said second artificial neural network using said second labeled data;
means for receiving the first question; and
means for associating a question category with the first question using said second artificial neural network. - View Dependent Claims (18)
-
-
19. A computer program product, comprising a computer-readable medium having computer program instructions embodied thereon to cause a computer processor to implement a method for automatically classifying a first question, the method comprising:
-
automatically labeling said unlabeled data to produce first labeled data using a first artificial neural network, said first artificial neural network comprising a first set of weights;
transferring said first set of weights to a second artificial neural network;
receiving second labeled data comprising a second question and a corresponding answer;
training said second artificial neural network using said second labeled data;
receiving the first question; and
associating a question category with the first question using said second artificial neural network.
-
Specification