MRE: A Study on Evolutionary Language Understanding

Donghui Feng, Eduard Hovy

2005

Abstract

The lack of well-annotated data is always one of the biggest problems for most training-based dialogue systems. Without enough training data, it’s almost impossible for a trainable system to work. In this paper, we explore the evolutionary language understanding approach to build a natural language understanding machine in a virtual human training project. We build the initial training data with a finite state machine. The language understanding system is trained based on the automated data first and is improved as more and more real data come in, which is proved by the experimental results.

References

  1. Swartout, W., et al.: Toward the Holodeck: Integrating Graphics, Sound, Character and Story. Proceedings of 5th International Conference on Autonomous Agents. (2001)
  2. Eugene Charniak. Statistical Parsing with a Context-free Grammar and Word Statistics. AAAI-97, (1997) pp. 598-603
  3. Michael Collins. Three Generative, Lexicalised Models for Statistical Parsing. Proc. of the 35th ACL, (1997) pp. 16-23
  4. S. Miller, R. Bobrow, R. Ingria, and R. Schwartz. Hidden Understanding Models of Natural Language, Proceedings of ACL Meeting, (1994) pp. 25-32
  5. Schwartz, R., Miller, S., Stallard, D., and Makhoul, J.: Language Understanding using hidden understanding models. In ICSLP'96 (1996.), pp. 997-1000
  6. Klaus Macherey, Franz Josef Och, Hermann Ney. Natural Language Understanding Using Statistical Machine Translation, EUROSPEECH, (2001) pp. 2205-2208, Denmark
  7. K. A. Papineni, et al. Feature-based language understanding, Proceedings of EuroSpeech'97, Greece, vol 3, (1997) pp. 1435-1438
  8. A.L. Gorin, G. Riccardi and J.H. Wright. How may I help you?, Speech Communication, vol. 23, (1997) pp. 113-127
  9. W. Minker, S.K. Bennacef, and J.L. Gauvain. A Stochastic Case Frame Approach for Natural Language Understanding, Proc. ICSLP, (1996) pp. 1013-1016
  10. D. Gildea and D. Jurafsky. Automatic Labeling of Semantic Roles, Computational Linguistics, 28(3) (2002) 245-288 14
  11. Michael Fleischman, Namhee Kwon, and Eduard Hovy. Maximum Entropy Models for FrameNet Classification. EMNLP, Sapporo, Japan. (2003)
  12. G. Sampson, 1996. Evolutionary Language Understanding, Cassell, NY/London (1996)
  13. Peter F. Brown, et al. Class-Based n-gram Models of Natural Language, Computational Linguistics, 18 (4), (1992) 467-479
Download


Paper Citation


in Harvard Style

Feng D. and Hovy E. (2005). MRE: A Study on Evolutionary Language Understanding . In Proceedings of the 2nd International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2005) ISBN 972-8865-23-6X, pages 45-54. DOI: 10.5220/0002562300450054


in Bibtex Style

@conference{nlucs05,
author={Donghui Feng and Eduard Hovy},
title={MRE: A Study on Evolutionary Language Understanding},
booktitle={Proceedings of the 2nd International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2005)},
year={2005},
pages={45-54},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002562300450054},
isbn={972-8865-23-6X},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2005)
TI - MRE: A Study on Evolutionary Language Understanding
SN - 972-8865-23-6X
AU - Feng D.
AU - Hovy E.
PY - 2005
SP - 45
EP - 54
DO - 10.5220/0002562300450054