Talking to UNIX in English: an overview of UC

ABSTRACT

UC is a natural language help facility which advises users in using the UNIX operating system. Users can query UC about how to do things, command names and formats, online definitions of UNIX or general operating systems terminology, and debugging problems in using commands. UC is comprised of the following components: a language analyzer and generator, a context and memory model, an experimental common-sense planner, highly extensible knowledge bases on both the UNIX domain and the English language, a goal analysis component, and a system for acquisition of new knowledge through instruction in English. The language interface of UC is based on a “phrasal analysis” approach which integrates semantic, grammatical and other types of information. In addition, it includes capabilities for ellipsis resolution and reference disambiguation.

REFERENCES

• 1: Arens, Y. Using languages and context in the analysis of text. In the Proceedings of the Seventh International Joint Conference on Artificial Intelligence, Vancouver, B.C., Canada, August 1981.
• 2: Arens, Y. The context model: Language understanding in context. In the Proceedings of the Fourth Annual Conference of the Cognitive Science Society, Ann Arbor, Michigan, August 1982.
• 3: Brachman, R., Bobrow, R., Cohen, P., Klovstad, J., Webber, B.L., and Woods, W.A. Research in natural language understanding. Tech. Rpt. 4274, Bolt, Beranek and Newman Inc., Cambridge, MA, 1979.
• 4: Burton, R.R. Semantic grammar: An engineering technique for constructing natural language understanding systems. BBN Rpt. 3453, Bolt Beranek and Newman, Inc., Cambridge, MA, December 1976.
• 5: David N. Chin, Knowledge structures in UC, the UNIX Consultant, Proceedings of the 21st annual meeting on Association for Computational Linguistics, June 15-17, 1983, Cambridge, Massachusetts [doi>10.3115/981311.981342]
• 6: Chin, D.N. A case study of knowledge representation in UC. In the Proceedings of the Eighth International Joint Conference on Artificial Intelligence, Karlsruhe, Germany, August 1983.
• 7: Chin, D.N. An analysis of scripts generated in writing between users and computer consultants. AFIPS Proceedings of the National Computer Conference 53. Las Vegas, NV, July 1984.
• 8: Deering, M., Faletti, J., and Wilensky, R. PEARL: An efficient language for artificial intelligence programming. In the Proceedings of the Seventh International Joint Conference on Artificial Intelligence, Vancouver, B.C. Canada, August 1981.
• 9: Deering, M., Faletti, J., and Wilensky, R. The PEARL users' manual. Berkeley Electronic Research Laboratory Memorandum UCB/ ERL/M82/19, Berkeley, CA, March 1982.
• 10: Douglass, R., and Hegner, S. An expert consultant for the UNIX system: Bridging the gap between the user and command language semantics. In the Proceedings of the Fourth National Conference of the Canadian Society for Computational Studies of Intelligence, University of Saskatchewan, Saskatoon, Canada, 1982.
• 11: Faletti, J. PANDORA--A program for doing common-sense planing in complex situations. In Proceedings of the Second Annual National Intelligence Conference, Pittsburgh, PA, August 1982, 185-188.
• 12: Grosz, B.J. The representation and use of focus in a system for understanding dialogs. Proceedings of the Fifth International Joint Conference on Artificial Intelligence, Carnegie-Mellon University, Pittsburgh, PA, 1977, 67-76.
• 13: Hayes, J.H., and Carbonell, J.G. Multi-strategy construction-specific parsing for flexible database query and update. In the Proceedings of the Seventh International Joint Conference on Artificial Intelligence, Vancouver, B.C. Canada, August 1981, 432-439.
• 14: Philip J. Hayes , George V. Mouradian, Flexible parsing, Computational Linguistics, v.7 n.4, p.232-242, October-December 1981
• 15: Held, G.D., Stonebraker, M.R., and Wong, E. INGRES--A relational database system. AFIPS Conference Proceedings 44, (1975), 409-416.
• 16: Gary G. Hendrix , Earl D. Sacerdoti , Daniel Sagalowicz , Jonathan Slocum, Developing a natural language interface to complex data, ACM Transactions on Database Systems (TODS), v.3 n.2, p.105-147, June 1978 [doi>10.1145/320251.320253]
• 17: Hobbs, J., and Evans, D. Conversation as planned behavior. Cognitive Science 4, 4 (Oct. 1980), 349-377.
• 18: Jacobs, P. Generation in a natural language interface. In the Proceedings of the Eighth International Joint Conference on Artificial Intelligence. Karlsruhe, Germany, August 1983, 610-612.
• 19: Lebowitz, M. Generalization and memory in an integrated understanding system. Department of Computer Science Tech. Rpt. 186. Yale University, New Haven, CT, 1980.
• 20: Luria, M. Dividing up the question-answering process. In the Proceedings of the Second Annual National Artificial Intelligence Conference, Pittsburgh, PA, August 1982, 71-74.
• 22: Reichman, R. Conversational coherency. Cognitive Science 3, 4 (1978), 283-327.
• 23: Riesbeck, C.K. Conceptual analysis. In Conceptual Information Processing, Schank, R.C., ed., Elsevier North-Holland Inc., New York, NY, 1975, 83-158.
• 24: Jane J. Robinson, DIAGRAM: a grammar for dialogues, Communications of the ACM, v.25 n.1, p.27-47, Jan. 1982 [doi>10.1145/358315.358387]
• 25: Roger C. Schank, Conceptual Information Processing, Elsevier Science Inc., New York, NY, 1975
• 26: Roger C. Schank , Michael Lebowitz , Lawrence Birnbaum, An integrated understander, Computational Linguistics, v.6 n.1, p.13-30, January-March 1980
• 27: Waltz, D.L., Finin, T., Green, F., Conrad, F., Goodman, B., and Hadden, G. The PLANES system: Natural language access to a large database. Coordinated Science Laboratories Tech. Rpt. T-34, University of Illinois, Urbana, IL, 1976.
• 28: Wilensky, R, Meta-planning: Representing and using knowledge about planning in problem solving and natural language understanding, Cognitive Science 5, 3 (1981), 197-234.
• 29: Wilensky, R, A knowledge-based approach to natural language processing: A progress report, In the Proceedings of the Seventh International Joint Conference on Artificial Intelligence. Vancouver, B.C, Canada, August 1981, 25-30.
• 30: Wilensky, R. Planning and understanding. Addison-Wesley. Reading, MA, 1983.
• 31: Wilensky, R., and Morgan, M. One analyzer for three languages. Berkeley Electronic Research Laboratory Memorandum UCB/ERL/ M81/67. Berkeley, CA, (September 1981).
• 32: W. A. Woods, Transition network grammars for natural language analysis, Communications of the ACM, v.13 n.10, p.591-606, Oct. 1970 [doi>10.1145/355598.362773]

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.0 General

          Nouns: UNIX

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Natural language

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Human Factors, Languages, Performance, Theory

Keywords:
ellipsis, goal analysis, memory models, natural dialogue, reference disambiguation