AMITIES

Description

AMITIES is an international (EU/US) consortium which is developing novel technologies for building empirically induced dialogue processors to support automated multilingual human-computer interaction with information and services. The consortium is funded jointly by the European Commission and the U.S. Defense Advanced Research Projects Agency, as well as through contributions from the consortium’s industrial partners. This approx. Euro 7.5 mln ($6.8 mln) project has been launched on May 14th 2001 and will be completed by April 2004. AMITIES partners include:

University of Sheffield (UK)

University at Albany (USA)

LIMSI-CNRS (FR)

VECSYS (FR)

Duke University (USA)

General Electric Company (USA)

VIEL (FR)

Professors Yorick Wilks (Sheffield) and Tomek Strzalkowski (Albany) are project codirectors on both sides of the Atlantic.

ubiquitous dialoguing

The central thrust of the work is the synthesis of dialogue systems from large corpora of recorded human-human and human-computer conversations. The project will extend techniques that have been successful for creating robust parsers and speech recognizers to the area of dialogue systems by utilizing probabilistic models and learning technologies.

The AMITIES work is funded on the belief that such methodologies have matured to the point where they can be applied to efficient and reliable automated call center systems. Once such technologies are operative at the dialogue level, they can be extended to new languages, applications, and user groups.

AMITIES will allow EU and US citizens to continuously access information and assistance from commercial companies via the telephone and the Internet using their native languages in a natural interactive dialogue. AMITIES technology will be showcased at the commercial call centers operated by the consortium members across EU and the US. The consortium will seek out other potential applications, such as health insurance services and public assistance applications. Data will be collected at such sites for evaluation and demonstration purposes so as to ensure that the project covers the needs of these applications, which is essential for the exploitability of the results.

tomorrow's call centers

For more information, please contact Prof. Tomek Strzalkowski, at 442-2608 or by email at tomek [at] albany [dot] edu

Related Publications

T. Strzalkowski, The Dialogue Game, Designing Task-Oriented Spontaneous Dialogue System for Automated Call Centers, Invited presentation at 3rd International Workshop on Human-Computer Conversation, Bellagio, Italy, July 2000

A. Bagga, T. Strzalkowski and B. Wise, PartsId: A Dialogue-Based System for Finding Parts for Medical Systems, Proceedings of 6th Applied Natural Language Conference (ANLP-2000), Seattle, WA, May, 2000, pp. 182-190

A. Bagga and T. Strzalkowski, Using Terminology in a Spoken Dialogue System for Identifying Medical Parts, In Proceedings of the Terminology Resources and Computation Workshop at the Second International Conference on Language Resources and Evaluation (LREC-2000), pp. 71-75. 2000

NOTE: To download these papers and to find other publications, see the papers section.

IARPA