PEGASUS: A Spoken Language Interface for On-Line Air Travel Planning

Zue, Victor W.; Seneff, Stephanie; Polifroni, Joseph; Phillips, Michael J.; Pao, Christine; Goddeau, David; Glass, James; Brill, Eric

doi:10.21236/ada460588

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Response Generation Natural language generation in our conversational systems is achieved using GENESIS, which has been ported to five domains and seven languages [8]. 2 GENESIS serves the dual role of paraphrasing meaning representations and generating responses to the user. The input to GENESIS is a semantic frame created by TINA, which may be augmented to include information returned from a database query.…”

Section: Meaning Representationmentioning

confidence: 99%

“…Over the years, we have developed a series of conversational systems with increasing complexity, including VOYAGER for urban navigation and exploration [1], PEGASUS for air travel planning [2], and GALAXY for on-line, multi-domain information access [3]. A cornerstone of our research effort throughout this period has been the development of multilingual conversational systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilingual human-computer interactions: from information access to language learning

Zue¹,

Seneff²,

Polifroni³

et al. 1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

Self Cite

View full text Add to dashboard Cite

This paper describes our recent work in developing multilingual conversational systems that support human-computer interactions. Our approach is based on the premise that a common semantic representation can be extracted from the input for all languages, at least within the context of restricted domains. In our design of such systems, language dependent information is separated from the system kernel as much as possible, and encoded in external data structures. The internal system manager, discourse and dialogue component, and database are all maintained in a language transparent form. We will describe two possible application areas for such multilingual capabailities: on-line information access using multilingual spoken dialogue, and the learning and maintenance of a foreign language using a multilingual conversational system.

show abstract

Section: Meaning Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multilingual human-computer interactions: from information access to language learning

Zue¹,

Seneff²,

Polifroni³

et al. 1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Multi-modal conversation systems are designed to realize natural communication between a human and a computer through the utilization of computer graphics and spoken language [1]. In this approach, the point o f the interface was to provide the users with an easy and nat-ATR Media Integration & Communications Research Laboratories, 2{2 Hikaridai Seika-cho Soraku-gun Kyoto 619{0288, Japan.…”

Section: Introductionmentioning

confidence: 99%

Establishing affinity relationships toward agents: effects of sympathetic agent behaviors toward human responses

Takeuchi

Katagiri²

Proceedings. IEEE 8th International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises (WET ICE'9

View full text Add to dashboard Cite

Abstract| People tend to favor the opinions of those who previously made the same decisions as theirs. We conducted an experiment t o i n v estigate the eect of sharing opinions with interface agents on subsequent human behaviors. Three agents with distinctive appearances were used in the experiment. In the rst stage, several questions are posed to a subject by the Presider agent, and the Agreeable agent shows explicit agreement to all of the answers by the subject, whereas the Neutral agent doesn't show any agreement. Then, in the second stage, both the Agreeable and Neutral agents state their own opinions to a question by the Presider agent, and the subject is required to choose between the two. All possible assignments (six patterns) of the roles of Presider, Agreeable and Neutral to the three agents were included in the experiment to exclude the possibility of decisions based on subjects liking a particular agent's appearance. The Agreeable agent was consistently in favor of the subject's decisions. We examined how the subject indicates sympathetic responses to the Agreeable agent after he/she interacts with agents. The results showed that people tend to behave favorably toward opinions of agents that previously agreed with their decisions. This suggests that Human-Computer interaction has the same social dynamics as Human-Human interaction.

show abstract

PEGASUS: A Spoken Language Interface for On-Line Air Travel Planning

Cited by 2 publications

References 11 publications

Multilingual human-computer interactions: from information access to language learning

Multilingual human-computer interactions: from information access to language learning

Establishing affinity relationships toward agents: effects of sympathetic agent behaviors toward human responses

Contact Info

Product

Resources

About