Meta learning for question classification

Details Meta learning for question classification Meta learning for question classification

2006-04-24

2009-10-13

Vincent, David R (Department: 2129)

Data processing: artificial intelligence

Neural network

Learning task

C706S025000

Reexamination Certificate

active

07603330

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.

REFERENCES:
patent: 4638445 (1987-01-01), Mattaboni
patent: 4884217 (1989-11-01), Skeirik et al.
patent: 5392382 (1995-02-01), Schoppers
patent: 5717598 (1998-02-01), Miyakawa et al.
patent: 5774632 (1998-06-01), Kaske
patent: 5889926 (1999-03-01), Bourne et al.
patent: 6135396 (2000-10-01), Whitfield et al.
patent: 6247008 (2001-06-01), Cambot et al.
patent: 6353814 (2002-03-01), Weng
patent: 6493607 (2002-12-01), Bourne et al.
patent: 6581048 (2003-06-01), Werbos
patent: 6604094 (2003-08-01), Harris
patent: 6687685 (2004-02-01), Sadeghi et al.
patent: 6862497 (2005-03-01), Kemp et al.
patent: 2002/0129015 (2002-09-01), Caudill et al.
patent: 2003/0093514 (2003-05-01), Valdes et al.
patent: 2004/0111408 (2004-06-01), Caudill et al.
patent: 2005/0278362 (2005-12-01), Maren et al.
patent: 2006/0004683 (2006-01-01), Talbot et al.
patent: WO 02/057961 (2002-07-01), None
Fei et al., Question Classification for E-learning by Artificial Neural Network, 2003.
Pratt, Non-literal Transfer Among Neural Network Learners, 1993.
Waibel et al., Modularity and Scaling in Large Phonemic Neural Networks, 1989.
Klein, D. et al. “Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank,” Proceedings of the 39thAnnual Meeting of the ACL, 2001, 8 pages.
PCT International Search Report and Written Opinion, PCT/US06/23554, Mar. 20, 2008, 8 pages.
PCT International Search Report and Written Opinion, PCT/US06/02204, Feb. 13, 2008, 7 pages.
PCT International Search Report and Written Opinion, PCT/US07/61061, Nov. 26, 2007, 8 pages.
PCT International Search Report and Written Opinion, PCT/US06/23822, Oct. 9, 2007, 9 pages.
Zhang, W., “Representation of Assembly and Automatic Robot Planning by Petri Net,” IEEE Transactions on Systems, Man and Cybernetics, Mar./Apr. 1989, pp. 418-422, vol. 19, No. 2.
Arroyo, A.A., “A Prototype Natural Language Processing System for Small Autonomous Agents,” Machine Intelligence Laboratory, Department of Electrical and Computer Engineering, University of Florida, pp. 1-6.
Baumgartner, P. et al., “Automated Reasoning Support for SUMO/KIF,” Max-Planck-Institute for Computer Science, Saarbrucken, Germany, Feb. 4, 2005, pp. 1-18.
Brill, Eric A Simple-Rule Based Part-of-Speech Tagger, Proceedings of ANLP-92, 34d Conference on Applied Natural Language Processing, Trento, IT, 1992, pp. 1-4.
Gupta, Rakesh et al., “Common Sense Data Acquisition for Indoor Mobile Robots,” Nineteenth National Conference on Artificial Intelligence (AAAI-04), Jul. 25-29, 2004, pp. 1-6.
Kalinichenko, L.A., “Rule-Based Concept Definitions Intended for Reconciliation of Semantic Conflicts in the Interoperable Information Systems,” Institute for Problems of Informatics, Proceedings of the Second International Baltic Workshop on DB and IS, Jun. 1996, pp. 1-12.
Kurfess, F.J., “CPE/CSC 481: Knowledge-Based Systems,” Jun. 2005, Retrieved from the Internet<URL:www.csc.calpoly.edu/˜fkurfess/Courses/481/Slides/>.
Laskey, K.B., “Knowledge Representation and Inference for Multisource Fusion,” Apr. 2002, Retrieved from the Internet<URL:www.msri.org/publications/In/hosted
as/2002/laskey/1/banner/01.html>.
“Markov Chain,” Wilipedia, the free encyclopedia, [online] [Retrieved on Mar. 30, 2006] Retrieved from the Internet<URL: http://en.wikipedia.org/wiki/Markov—chain>.
Matsuda, Y. et al., “Synthesis of Multiple Answer Evaluation Measures Using a Machine Learning Technique for a QA System,” Proceedings of the NTCIR-5 Workshop Meeting, Dec. 6-9, 2005, 7 pages.
“Mixed-Initiative Activity Planning,” NASA Ames Research Center, 2004, [online] [Retrieved on Nov. 21, 2006] Retrieved from the Internet<URL:http://ic.arc.nasa.gov/publications/pdf/Mixed—Initiative—Act.pdf>.
Russell, S. J., et al., Artificial Intelligence-A Modern Approach, Second Edition, Prentice Hall, Pearson Education, Inc., New Jersey 2003/1995, pp. 462-536.
Setiono, R. et al., “Automatic Knowledge Extraction from Survey Data: LearningM-of-NConstructs Using a Hybrid Approach,” Journal of the Operational Research Society, 2005, pp. 3-14, vol. 56.
Soricut, R. et al., “Automatic Question Answering: Beyond the Factoid,” [online] [Retrieved on Nov. 28, 2006] Retrieved from the Internet<URL:http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/104—Paper.pdf>.
Stork, David G., “Open Mind Initiative,” ICDAR99, Bangalore, India, pp. 1-28.
Eagle, N., et al., “Context Sensing using Speech and Common Sense,” Proceedings of the NAACL/HLT 2004 Workshop on Higher-Level Linguistic and Other Knowledge for Automatic Speech Processing, 2004.
Liu, H., et al., “ConceptNet—a practical commonsense reasoning tool-kit,” BT Technology Journal, Oct. 2004, p. 211-226, vol. 22, No. 4.
Liu, H., et al., “OMCSNet: A Commonsense Inference Toolkit,” 2003, [online] [Retrieved on Jan. 26, 2009] Retrieved from the internet <URL:http://web.media.mit.edu/˜push/OMCSNet.pdf>.
Singh, P., et al., “LifeNet: A Propositional Model of Ordinary Human Activity,” Proceedings of the Workshop on Distributed and Collaborative Knowledge Capture (DC-KCAP) at KCAP 2003, 2003, 7 Pages.

Affiliated with

Also associated with

Rating

Meta learning for question classification does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Meta learning for question classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Meta learning for question classification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4138790