An evaluation of strategies for selectively verifying utterance meanings in spoken natural language dialog

Smith, Ronnie W.

doi:10.1006/ijhc.1997.0184

Cited by 17 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative programming approach is to use such questions to generate expectations about what the user will say and use this to aid subsequent interpretations of the user input (e.g. Smith, 1998). This is a potentially less prescriptive approach to dialogue constraint, allowing the user to change topics if they desire (i.e.…”

Section: Semantic Constraintmentioning

confidence: 98%

“…For instance, Smith (1998) describes an approach whereby an ungrammatical output from the speech recognizer is transformed into possible grammatical interpretations through trying various word insertions, deletions and substitutions. Each of these transformations will have an associated cost (for instance, the cost of substituting &&six'' for &&"x'' would be low as they sound so similar) and the lowest cost solution is preferred.…”

Section: Syntactic Constraintmentioning

confidence: 99%

See 1 more Smart Citation

Designing habitable dialogues for speech-based interaction with computers

Hone¹,

Baber²

2001

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

Habitability refers to the match between the language people employ when using a computer system and the language that the system can accept. In this paper, the concept of &&habitability'' is explored in relation to the design of dialogues for speechbased systems. Two studies investigating the role of habitability in speech systems for banking applications are reported. The "rst study employed a speech-driven automated teller machine (ATM), using a visual display to indicate available vocabulary. Users made several distinct types of error with this system, indicating that habitability in speech systems cannot be achieved simply by displaying the input language. The second study employed a speech input/speech output home banking application, in which system constraints were indicated by either a spoken menu of words or a &&query-style'' prompt (e.g. &&what service do you require?''). Between-subjects comparisons of these two conditions con"rmed that the &&menu-style'' dialogue was rated as more habitable than the &&query-style''. It also led to fewer errors, and was rated as easier to use, suggesting that habitability is a key issue in speech system usability. Comparison with the results of the "rst study suggests that for speech input, spoken menu prompts may be more habitable than similar menus shown on a visual display. The implications of these results to system design are discussed, and some initial dialogue design recommendations are presented.

show abstract

Section: Semantic Constraintmentioning

confidence: 98%

Section: Syntactic Constraintmentioning

confidence: 99%

Designing habitable dialogues for speech-based interaction with computers

Hone¹,

Baber²

2001

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

show abstract

“…One of the first dialog systems to make use of a hierarchy of dialog expectations was the Circuit Fix-It Shop (Smith et al, 1995) which was also one of the first working dialog systems to be carefully and extensively evaluated (Smith and Gordon, 1997) and (Smith, 1998). However, at the time, the ability to make use of large corpora in system development was largely non-existent.…”

Section: Pirate Methodology: What Should Dialog Expectation Mean?mentioning

confidence: 99%

Comparative Error Analysis of Dialog State Tracking

Smith

2014

Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

View full text Add to dashboard Cite

A primary motivation of the Dialog State Tracking Challenge (DSTC) is to allow for direct comparisons between alternative approaches to dialog state tracking. While results from DSTC 1 mention performance limitations, an examination of the errors made by dialog state trackers was not discussed in depth. For the new challenge, DSTC 2, this paper describes several techniques for examining the errors made by the dialog state trackers in order to refine our understanding of the limitations of various approaches to the tracking process. The results indicate that no one approach is universally superior, and that different approaches yield different error type distributions. Furthermore, the results show that a pairwise comparative analysis of tracker performance is a useful tool for identifying dialogs where differential behavior is observed. These dialogs can provide a data source for a more careful analysis of the source of errors.

show abstract

“…They also showed how to use such analyses to generate arti¢cial user data that can be used for evaluation purposes. Recall that other uses of arti¢cial data were discussed above, namely the use of computer^computer dialogue simulations in the context of evaluating mixed-initiative dialogue systems (Guinn, 1998;Ishizaki et al, 1999;Smith, 1998).…”

Section: Towards Empirical Methods^strengthening the Empirical Basis mentioning

confidence: 99%

“…Smith (1998) designed and evaluated strategies for dynamically deciding whether to con¢rm each user utterance during a task-oriented dialogue. Simulation results suggested that context-dependent adaptation strategies (e.g.…”

Section: Towards Spoken Dialogue Systemsmentioning

confidence: 99%

Untitled

Zukerman

Litman

2001

User Modeling and User-Adapted Interaction

View full text Add to dashboard Cite

Abstract. The ¢elds of user modeling and natural language processing have been closely linked since the early days of user modeling. Natural language systems consult user models in order to improve their understanding of users' requirements and to generate appropriate and relevant responses. At the same time, the information natural language systems obtain from their users is expected to increase the accuracy of their user models. In this paper, we review natural language systems for generation, understanding and dialogue, focusing on the requirements and limitations these systems and user models place on each other.We then propose avenues for future research.

show abstract

An evaluation of strategies for selectively verifying utterance meanings in spoken natural language dialog

Cited by 17 publications

References 12 publications

Designing habitable dialogues for speech-based interaction with computers

Designing habitable dialogues for speech-based interaction with computers

Comparative Error Analysis of Dialog State Tracking

Untitled

Contact Info

Product

Resources

About