Coping with aboutness complexity in information extraction from spoken dialogues

Kameyama, Megumi; Arima, I.

doi:10.21437/icslp.1994-25

Cited by 2 publications

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Turning pervasive computing into mediated spaces

Mark

1999

IBM Syst. J.

View full text Add to dashboard Cite

With pervasive computing, we envision a future in which computation becomes part of the environment. The computer forms (workstation, personal computer, personal digital assistant, game player) through which we now relate to computation will occupy only a small niche in this new computational world. Our relationship to pervasive computing will differ radically from our current relationship they have with computers. When computation becomes part of the environment, most human-computer interaction will be implicit, and it will have to take account of physical space. Physical space rarely matters in current human-computer interaction; but as computational devices become part of furniture, walls, and clothing, physical space becomes a necessary consideration. First, more than one person can occupy a space. Second, individuals within the space are doing things other than interacting with the computer: coming and going, and perhaps most strikingly, interacting with each other-not just with the computer. Finally, physical space provides a sense of place: individuals associate places with events and recurrent activities.

show abstract

Turning pervasive computing into mediated spaces

Mark

1999

IBM Syst. J.

View full text Add to dashboard Cite

show abstract

MET name recognition with Japanese FASTUS

Kameyama¹

1996

Proceedings of a Workshop on Held at Vienna, Virginia May 6-8, 1996 -

View full text Add to dashboard Cite

The first Japanese FASTUS was the MUC-5 Joint Venture system developed in 1993. Both the English and Japanese MUC-5 FASTUS systems used a graphical user interface called Grasper for rule definition, and recognized tie-up relationships among company organizations [1]. The performance of the Japanese FASTUS, together with other Japanese systems, demonstrated that the basic information extraction (IE) technology was portable to a language very different from English. The MUC-5 Japanese FASTUS gave us experience with 2-byte character input and JUMAN, a morphological analyzer developed at Kyoto University. The second Japanese FASTUS, called MIMI (for "ears" in Japanese), summarized spontaneous human-human dialogues, and was developed during 1993-1995. MIMI was also Grasper-based, but its input was ASCII character "romaji" with spaces between words, and it had a 3,000-word dictionary in the domain of conference room scheduling [4, 5, 6]. During 1994-1995, the English FASTUS infrastructure underwent a number of changes, the most significant of which was the transition from Grasper to a declarative pattern specification language called FastSpec. FastSpec enables a fast cycle of rule specification, compilation, and testing during development [21. *MET FASTUS was developed under SRI IR&D support.

show abstract

Coping with aboutness complexity in information extraction from spoken dialogues

Cited by 2 publications

References 0 publications

Turning pervasive computing into mediated spaces

Turning pervasive computing into mediated spaces

MET name recognition with Japanese FASTUS

Contact Info

Product

Resources

About