Abstract
In almost all computer applications, users must enter correct words for the desired objects or actions. For success without extensive training, or in first-tries for new targets, the system must recognize terms that will be chosen spontaneously. We studied spontaneous word choice for objects in five application-related domains, and found the variability to be surprisingly large. In every case two people favored the same term with probability <0.20. Simulations show how this fundamental property of language limits the success of various design methodologies for vocabulary-driven interaction. For example, the popular approach in which access is via one designer's favorite single word will result in 80-90 percent failure rates in many common situations. An optimal strategy, unlimited aliasing, is derived and shown to be capable of several-fold improvements.
- 1 Card. S., Moran. T.P. and Newell, A. The Psychology of Hunra~~- Compufer Interaction. Lawrence Erlbaum Associates. Hillsdale. N.J. 1983. Google ScholarDigital Library
- 2 Dumais. ST., and Landauer. T.K. Describing categories of objects for menu retrieval systems. Brhavior Research Methods. lrrslrunmrts. b Compu~us, 16. 2 (Apr. 1984). 242-248.Google Scholar
- 3 Furnas. G.W. Experience with an adaptive indexing scheme. Hunla~~ Factors in Computer Sysfenls, CHI '85 Proceedings. Conference held in San Francisco, CA, April 15-18.1985. 131-135. Google ScholarDigital Library
- 4 Furnas, G.W., Landauer, T.K. Gomez. L.M. and Dumais. ST. Statistical semantics: Analysis of the potential performance of key-word information systems. Bell System Technical /oumal. 62. 6 (Jul.-Aug. 1983). 1753-1806.Google Scholar
- 5 Gomez. L.M. and Lochbaum, CC. People can retrieve more objects with enriched key-word vocabularies. But is there a human performance cost? In B. Shackel (Ed.) Human-Computer Inleractm- Interact '84, North-Holland. Amsterdam. 257-261.Google Scholar
- 6 Good, M.D., Whiteside. J.A. Wixon. D. R. and Jones. S.J. Building a user-derived interface. Comn~un. ACM, 27, 10 (Oct. 1984). 1032-1043. Google ScholarDigital Library
- 7 Herdan. G. Type Tokerr Mathematics: A Textbook of Mathenratical Linguisfics, S-Gravenhage. Mouton. 1960.Google Scholar
- 8 { Landauer. T.K., Galotti. K. and Hartwell. S. Natural command names and initial learning: A study of text editing terms. Conrntun. ACM, 26, 7 (Jul. 1983). 495-503. Google ScholarDigital Library
- 9 Reisner. P. Construction of a growing thesaurus by conversational interaction in a man-machine system. Proceedings of the American Dmmw~fafim Insfifute. 26th Annual Meeting. Chicago, Ill. October 1963.Google Scholar
- 10 Reisner. P. Evaluation of a 'Growing Thesaurus'. Research Paper RC-1662. August 9. 1966. IBM Watson Research Center. Yorktown Heights, N.Y.Google Scholar
- 11 { Roberts. T.L. and Moran. T.P. The evaluation of text editors: Methodology and empirical results. C~vvn~utt. ACM, 26. 4 (Apr. 1983). 265-283. Google ScholarDigital Library
- 12 Sparck-Jones. K. A Statistical interpretation of term specificity and its application in retrieval. I. LXX. 28. 1 (Mar. 1972). 11-21.Google Scholar
- 13 Whalen, T. and Latremouille. S. The effectiveness of a treestructured index when the existence of information is uncertain. Tcledort Behavioral Research 2: The Drsip of Vidrotex Trre Itldiccs. Ottawa, Canada: Department of Communications. (May 1981). pp. 3-12.Google Scholar
- 14 Zipf, G.K. Hunra~l Behavior wd the Prirmple of Least Effort. AII Irtfnrdurtuw fn Human Emlogy. Addison-Wesley. Reading. Mass. 1949.Google Scholar
Index Terms
- The vocabulary problem in human-system communication
Recommendations
Building Medium-Vocabulary Isolated-Word Lithuanian HMM Speech Recognition System
In this paper, the opening work on the development of a Lithuanian HMM speech recognition system is described. The triphone single-Gaussian HMM speech recognition system based on Mel Frequency Cepstral Coefficients (MFCC) was developed using HTK toolkit. ...
Automatic detection of new words in a large vocabulary continuous speech recognition system
HLT '89: Proceedings of the workshop on Speech and Natural LanguageIn practical large vocabulary speech recognition systems, it is nearly impossible for a speaker to remember which words are in the vocabulary. The probability of the speaker using words outside the vocabulary can be quite high. For the case when a ...
Unlimited vocabulary speech recognition for agglutinative languages
HLT-NAACL '06: Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational LinguisticsIt is practically impossible to build a word-based lexicon for speech recognition in agglutinative languages that would cover all the relevant words. The problem is that words are generally built by concatenating several prefixes and suffixes to the ...
Comments