Abstract
The L0 project at ICSI and UC Berkeley attempts to combine not only vision and natural language modelling, but also learning. The original task was put forward in (Feldman et al. 1990a) as a touchstone task for AI and cognitive science. The task is to build a system that can learn the appropriate fragment of any natural language from sentence-picture pairs. We have not succeeded in building such a system, but we have made considerable progress on component subtasks and this has led in a number of productive and surprising directions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Berlin, Brent & Kay, Paul (1969). Basic Color Terms: Their Universality and Evolution. University of California Press, Berkeley.
Brugman, Claudia (1983). The Use of Body-Part Terms as Locatives in Chalcatongo Mixtec. In Report No. 4 of the Survey of California and other Indian Languages, 235–290. University of California, Berkeley.
Feldman, Jerome. A. (1989). Neural Representation of Conceptual Knowledge. In Lynn Nadel et al. (eds.) Neural Connections, Mental Computation, 68–103. Cambridge, Mass.: MIT Press.
Feldman, Jerome, Lakoff, George, Stolcke, Andreas & Weber, Susan Hollback (1990a). Miniature Language Acquisition: A Touchstone for Cognitive Science. In Proceedings of The 12th Annual Conference of the Cognitive Science Society, 686–693. Cambridge, Mass.: MIT Press.
Feldman, Jerome, Susan Hollbach Weber & Andreas Stolcke. (1990b). A Testbed for the Miniature Language L0. In Proceedings of The 5th Rocky Mountain Conference on Artificial Intelligence, 25–30. New Mexico State University, Las Cruces, N.M.
Gull, S. F. (1988). Bayesian Inductive Inference and Maximum Entropy. In G. J. Erickson & C. R. Smith (eds.) Maximum Entrophy and Bayesian Methods in Science and Engineering, Volume 1: Foundations, 53–74. Dordrecht: Kluwer.
Guyon, I., Albrecht, P., LeCun, Y., Denker, J. & Hubbard, W. (1991). Design of a Neural Network Character Recognizer for a Touch Terminal. Pattern Recognition 24: 105–119.
Horning, James Jay (1969). A Study of Grammatical Inference. Technical Report CS 139, Computer Science Department, Stanford University, Stanford, Ca.
Jurafsky, Daniel (1992). An On-line Computational Model Of Human Sentence Interpretation. Berkeley, CA: Dept. of Computer Science, University of California dissertation. Available as Technical Report UCB/CSD 92/767.
Keeler, James, Rumelhart, David & Leow, Wee-Kheng (1991). Integrated Segmentation and Recognition of Hand-Printed Numerals. Technical Report ACT-NN-010-91, Microelectronics and Computer Technology Corporation.
Lakoff, George (1987). Women, Fire, and Dangerous Things: What Categories Reveal about the Mind. University of Chicago Press.
Lakoff, George (1992). What is Metaphor? In K. J. Holyoak & J. A. Barnden (eds.) Advances In Connectionist and Neural Computational Theory, Vol. 2: Analogical Connections, Ablex.
LeCun, Yann (1989). Generalization and Network Design Strategies. Technical Report CRG-TR-89-4, Connectionist Research Group, University of Toronto.
Mozer, Michael, Zemel, Richard & Behrmann, Marlene (1991). Learning to Segment Images Using Dynamic Feature Binding. Technical Report CU-CS-540-91, Dept. of Computer Science, University of Colorado at Boulder.
Nenov, Valerity I. & Dyer, Michael G. (1993). Perceptually Grounded Language Learning: Part I — A Neural Network Architecture for Robust Sequence Association. Connection Science 5.
Nenov, Valerity I. & Dyer, Michael G. (1994). Perceptually Grounded Langugae Learning: Part 2 — DETE: A Neural/Procedural Model. Connection Science 6.
Nielsen, M., Plotkin, G. & Winskel, G. (1981). Petri Nets, Event Structures, and Domains, Part I. Theoretical Computer Science 13.
Omohundro, Stephen M. (1992). Best-first Model Merging for Dynamic Learning and Recognition. In John E. Moody, Steve J. Hansion & Richard P. lippman (eds.) Advances in Neural Information Processing Systems 4, 958–965. San Mateo, CA: Morgan Kaufmann.
Regier, Terry (1992). The Acquisition of Lexical Semantics for Spatial Terms: A Connectionist Model of Perceptual Categorization. Computer Science Division, EECS Department, University of California at Berkeley dissertation, avaiable as Technical Report TR-92-062, International Computer Science Institute, Berkeley.
Regier, Terry (1993). Two Predicted Universals in the Semantics of Space. In Proceedings of The Nineteenth Annual Meeting of the Berkeley Linguistics Society. University of California, Berkeley.
Rissanen, Jorma (1983). A Universal Prior for Integers and Estimation by Minimum Description Length. The Annals of Statistics 11: 416–431.
Rumelhart, David E., Hinton, Geoffrey E. (eds.) & Williams, Ronald J. (1986). Learning Internal Representations by Error Propagation. In James L. McClelland & David E. Rumelhart (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 318–362. MIT Press.
Shieber, Stuart M. (1986). An Introduction to Unification-Based Approaches to Grammar. Number 4 in CSLI Lecture Note Series. Stanford, Ca.: Center for the Study of Language and Information.
Siskind, Jeffrey Mark (1992). Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition. Cambridge, Mass.: Massachussetts Institute of Technology dissertation.
Stolcke, Andreas (1990). Learning Feature-Based Semantics with Simple Recurrent Net-works. Technical Report TR-90–015, International Computer Science Institute, Berkeley, CA.
Stolcke, Andreas (1994). Bayesian Learning of Probabilistic Language Models. Berkeley, CA: University of California Dissertation.
Stolcke, Andreas & Omohundro, Stephen (1993). Hidden Markov Model Induction by Bayesian Model Merging. In Stephen Jose Hanson, Jack D. Cowan & C. Lee Giles (eds.) Advances in Neural Information Processing Systems 5, 11–18. San Mateo, CA: Morgan Kaufmann.
Stolcke, Andreas. & Omohundro, Stephen (1994). Inducing Probabilistic Grammars by Bayesian Model Merging. In Rafael C. Carrasco & Jose Oncina (eds.) Grammatical Inference and Applications. Proceedings Second International Colloquium, Volume 862 of Lecture Notes in Artificial Intelligence, 106–118, Alicante, Spain. Springer Verlag.
Suppes, Patrick, Liang, Lin (eds.) & Bottner, Michael (1991) Complexity Issues in Robotic Machine Learning of Natural Language. In L. Lam & V. Naroditsky (eds.) Modeling Complex Phenomena, New York, N.Y.: Springer Verlag.
Wallace, C. S. & Freeman, P. R. (1987). Estimation and Inference by Compact Coding. Journal of the Royal Statistical Society, Series B 49: 240–265.
Weber, Susan Hollbach & Stolcke, Andreas (1990). L0: ATestbed for Miniature Language Acquisition. Technical Report TR-90–010, International Computer Science Institute, Berkeley, CA.
Whorf, Benjamin Lee (1956). Language, Thought, and Reality. Cambridge, MA: MIT Press. (John B. Carroll, ed.).
Wooters, Chuck & Stolcke, Andreas (1994). Multiple-Pronunication Lexical Modeling in a Speaker-Independent Speech Understanding System. In Proceedings of The International Conference on Spoken Language Processing, Volume 3, 1363–1366, Yokohama.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Kluwer Academic Publishers
About this chapter
Cite this chapter
Feldman, J., Lakoff, G., Bailey, D., Narayanan, S., Regier, T., Stolcke, A. (1996). L0 — The First Five Years of an Automated Language Acquisition Project. In: Mc Kevitt, P. (eds) Integration of Natural Language and Vision Processing. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-1639-5_15
Download citation
DOI: https://doi.org/10.1007/978-94-009-1639-5_15
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-7923-3944-1
Online ISBN: 978-94-009-1639-5
eBook Packages: Springer Book Archive