Language, mathematics and other dangerous things

ABSTRACT

We describe our original automata-theoretic, highly mathematical perspective on language representation and learning, and compare with some current research advances and some that are proposed. We find benefits of a mathematical approach to "real life" language learning by humans and today's machines, and review work of researchers who adapt such computational techniques to complex system development and language-related machine processes. Examples include design of communicating agents and proposed development of the Semantic Web. While emphasizing the success of a mathematical perspective on language representation and learning, we also note the danger of assuming that "perfect" results will always be produced by a mathematical approach.

REFERENCES

• 1: Nick Cercone , Lijun Hou , Vlado Keselj , Aijun An , Kanlaya Naruedomkul , Xiaohua Hu, From Computational Intelligence to Web Intelligence, Computer, v.35 n.11, p.72-76, November 2002 [doi>10.1109/MC.2002.1046978]
• 2: Chang, N. C. and Maia, T. V., 2001, "Grounded Learning of Grammatical Constructions", in (Cohen and Oates 2001): 10--15.
• 3: Cohen, P. R. and Oates, T., 2001, (Editors), Papers from the AAAI Spring Symposium on Learning Grounded Representations, Stanford University, March 2001, AAAI Press, SS-01-05.
• 4: Grossberg, S., 1994, "Fuzzy Neural Networks for Supervised Learning, Recognition and Prediction", Keynote Lecture, Joint Conference on Information Sciences, Duke University/Pinehurst NC, November, 1994.
• 5: Hang Li , Yunbo Cao , Cong Li, Using Bilingual Web Data to Mine and Rank Translations, IEEE Intelligent Systems, v.18 n.4, p.54-59, July/August 2003 [doi>10.1109/MIS.2003.1217628]
• 6: MacFarquhar, L., 2003, "The Devil's Accountant", The New Yorker, March 31, 2003: 64--79.
• 7: Powers, D., Harnad, S., Rayner, M. and Reeker, L., 1991, (Editors) Notes of the AAAI Spring Symposium on Machine Learning of Natural Language & Ontology, Stanford University, March 1991, released as German AI Institute, Kaiserslautern TR DFKI D-91-09.
• 8: Steffen Staab, Emergent Semantics, IEEE Intelligent Systems, v.17 n.1, p.78-86, January 2002 [doi>10.1109/5254.988491]
• 9: Steels, L., 2001,"The Role of Language in Learning Grounded Representations", in (Cohen and Oates 2001):80--83ff.
• 10: Steels, L., 2002, "Language Games for Emergent Semantics", in (Staab 2002): 83--85. Early Relevant References by the Author
• 11: Leona F. Fass, Learning context-free languages from their structured sentences, ACM SIGACT News, v.15 n.3, p.24-35, Summer-Fall 1983 [doi>10.1145/1008933.1008934]
• 12: L F Fass, On the inference of canonical context-free grammars, ACM SIGACT News, v.17 n.4, p.55-60, Spring 1986 [doi>10.1145/8307.8310]
• 13: Fass, L. F., 1996, "Minimal Language Learning", in Papers from the AAAI Spring Symposium on Computational Issues in Learning Models of Dynamical Systems, Stanford University, March 1996: 68--71.
• 14: Fass, L. F., 1998, "Learning (Language) Within a Context", Proceedings of the Third International Conference on Computational Intelligence and Neuroscience/Joint Conference on Information Sciences, Duke University/Research Triangle Park NC, October 1998, Vol II: 56--59.
• 15: Fass, L. F., 2001, "Language-Learning Determines All Learning", in (Cohen and Oates 2001): 26--27.

INDEX TERMS

Keywords:
agent design, grammatical inference, language representation, learning, the Semantic Web