NaturalJava: a natural language interface for programming in Java

ABSTRACT

NaturalJava is a prototype for an intelligent natural-language-based user interface for creating, modifying, and examining Java programs. The interface exploits three subsystems. The Sundance natural language processing system accepts English sentences as input and uses information extraction techniques to generate case frames representing program construction and editing directives. A knowledge-based case frame interpreter, PRISM, uses a decision tree to infer program modification operations from the case frames. A Java abstract syntax tree manager, TreeFace, provides the interface that PRISM uses to build and navigate the tree representation of an evolving Java program. In this paper, we describe the technical details of each component, explain the capabilities of the user interface, and present examples of NaturalJava in use.

REFERENCES

• 1: Biermann, A., Ballard, B., and Sigmon, A. An Experimental Study of Natural Language Programming. International Journal of Man-Machine Studies, Vol. 18, pp. 71-87, 1983.
• 2: Mary Elaine Califf , Raymond J. Mooney, Relational learning techniques for natural language information extraction, 1998
• 3: Dayne Freitag, Multistrategy Learning for Information Extraction, Proceedings of the Fifteenth International Conference on Machine Learning, p.161-169, July 24-27, 1998
• 4: Riloff, E. Automatically Generating Extraction Patterns horn Untagged Text. In Proceedings of the Thirteenth National Conference on Art$cial Intelligence, 1996.
• 5: Ellen Riloff, An empirical study of automated dictionary construction for information extraction in three domains, Artificial Intelligence, v.85 n.1-2, p.101-134, Aug. 1996 [doi>10.1016/0004-3702(95)00123-9]
• 6: Stephen Soderland, Learning Information Extraction Rules for Semi-Structured and Free Text, Machine Learning, v.34 n.1-3, p.233-272, Feb. 1999 [doi>10.1023/A:1007562322031]
• 7: Wonisch, M. Ein objektorientierter interaktiver Interpreter fur naturalichsprachliche Programmierung. Diploma Thesis. Lehrstuhl fCx MeBtechnik, RWTH Aachen, June 1995.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Experimentation, Human Factors

Keywords:
computer program editors, information extraction, intelligent user interfaces, natural language processing, programming environments