The vocabulary problem in human-system communication

  title={The vocabulary problem in human-system communication},
  author={George W. Furnas and Thomas K. Landauer and Louis M. Gomez and Susan T. Dumais},
  journal={Commun. ACM},
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… 

Figures and Tables from this paper

The Vocabulary Problem in Human-System Communication: an Analysis and a Solution

Many, many alternative access words are needed for users to get what they want from large and complex systems and an optimal strategy, unlimited aliasing, is derived and shown to be capable of several-fold improvements.

The Vocabulary Problem in Spoken Dialogue Systems

Designers of spoken dialogue systems need to be able to predict and constrain the words people use in speech directed at these systems, and the potential for variability in word choices is enormous.

Learning to Speak to a Spoken Language System: Vocabulary Convergence in Novice Users

It is found that novice users successfully learn the form of system requests, achieving a significant decrease in ill-formed utterances, but the working vocabulary on which novice users converge is significantly smaller than that of expert users, and their rate of speech recognition errors remains higher.

Natural Language Processing: A Human-Computer Interaction Perspective

Automated two-way entrainment to improve spoken dialog system performance

An approach to the use of lexical entrainment in Spoken Dialog Systems is proposed, which aims to increase the dialog success rate by adapting the lexical choices of the system to the user's Lexical choices.

Designing habitable dialogues for speech-based interaction with computers

The concept of “habitability” is explored in relation to the design of dialogues for speech-based systems, and suggests that for speech input, spoken menu prompts may be more habitable than similar menus shown on a visual display.

The Gesture Disagreement Problem in Free-hand Gesture Interaction

It is found that the chance for users to produce the same gesture for a given task is below 0.355 on average, and offering a set of gesture candidates can improve the agreement score.

The Vocabulary Problem in Collaboration

This research has shown the feasibility of an algorithmic approach to solving the vocabulary problem in collaboration by adopting automatic indexing, cluster analysis, and neural network classification techniques.

Adapting Spoken Dialog Systems Towards Domains and Users

This thesis built models to recognize the complex user intentions and enable the system to communicate with the user at the task level, in addition to the individual domain level, and believes that adaptation in these three levels can contribute to the quality of human-machine interactions.

Building Databases for the Computer-Based Memorization System.

The Computer-Based Memorization System (CBMS), which specifies the facts that students are to know and how well the facts are to be known, uses a compiled form of an associative network for its



Human factors and behavioral science: Statistical semantics: Analysis of the potential performance of key-word information systems

This paper examines how imprecision in the way humans name things might limit how well a computer can guess to what they are referring and finds that hit rates could be increased threefold by using norms on naming to pick optimal names.

Natural command names and initial learning: a study of text-editing terms

It is concluded that the design of user-compatible commands involves deeper issues than are captured by the slogan “naturalness” and generalizations to other situations will require further testing.

Building a user-derived interface

Through careful observation and analysis of user behavior, a mail interface unusable byNovices evolved into one that let novices do useful work within minutes.

The evaluation of text editors: methodology and empirical results.

The methodology has thus far been used to evaluate nine diverse text editors, producing an initial database of performance results that tells us not only about the editors but also about the users—the magnitude of individual differences and the factors affecting novice learning.

Describing categories of objects for menu retrieval systems

This research compares several different ways of describing ill-defined categories of objects using combinations of names and examples to provide a promising possibility, both as a means of flexibly naming new or difficult menu categories and as a methodological tool for studying certain categorization problems.

Experience with an adaptive indexing scheme

Experience with an adaptive technique for constructing a rich, empirically defined, frequency weighted index for new or intermittent users of computer systems is discussed.

Evaluation of a ‘Growing Thesaurus

  • Research Paper RC-1662. August
  • 1966

Hunra~l Behavior wd the Prirmple of Least Effort. AII Irtfnrdurtuw fn Human Emlogy

  • Hunra~l Behavior wd the Prirmple of Least Effort. AII Irtfnrdurtuw fn Human Emlogy
  • 1949

Construction of a growing thesaurus by conversational interaction in a man-machine system

  • Proceedings of the American Dmmw~fafim Insfifute. 26th Annual Meeting
  • 1963

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

  • 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