International Journal of Information Technology & Computer Science ( IJITCS )
In recent years the Spoken Language Processing field has been rapidly growing. Several human-machine systems with different characteristics have been developed, most of them without a distributed and scalable architecture. For instance, Olympus framework at the current version does not support multi-session. In addition, it uses the Phoenix parser without a dynamic grammar. In this paper we design a distributed, robust, scalable and multi-session architecture applied to a spoken dialog system along with a dynamic and self-learning Natural Language Understanding (NLU) mechanism. It is based on an extension of the basic Olympus framework. The implementation we propose, called OlympusP2P is built on a distributed and highly context-sensitive framework for applications that aim at interacting with users by using natural languages. OlympusP2P will soon available for researcher and application developer.
: Multi-Session, Dynamic Grammar Parser, Olympus
- Cheongjae Lee, Sangkeun Jung, Kyungduk Kim, Donghyeon Lee, and Gary Geunbae Lee, “Recent Approaches to Dialog Management for Spoken Dialog Systems,” Department of Computer Science and Engineering Pohang University of Science and Technology (POSTECH) Pohang, Republic of Korea, 2010
- Dan Bohus, Antoine Raux, Thomas K. Harris, Maxine Eskenazi, and Alexander I. Rudnicky, “Olympus: an open-source framework for conversational spoken language interface research”, in NAACL-HLT ’07: Proceedings of the Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, 2007
- Ward, W., Issar, S., “Recent improvements in the CMU spoken language understanding system”, in Proceedings of ARPA Human Language Technology Workshop, Plainsboro, NJ, 1994.
- Joseph Polifroni, and Stephanie Seneff, “Galaxy-II as an Architecture for Spoken Dialogue Evaluation”, Proc. LREC, 725-730, Athens, 2000
- Dan Bohus, Alexander I. Rudnicky, “The RavenClaw dialog management framework: Architecture and systems”, Computer Speech and Language, vol. 23, no. 3, 2009
- Minker, Chase, “Evaluating Parses for Spoken Language Dialogue Systems”, in First International Conference on Language Resources abd Evaluation – Proc. Workshop on The Evaluation of Parsing Systems, May 1998
- Bohus, D. & Rudnicky, A. 2002, November. Integrating multiple knowlege sources for utterance-level confidence annotation in the CMU Communicator spoken dialog system. (Tech. Rep. No. CMU-CS-02-190). Pittsburgh, Pennsylvania: School of Computer Science, Carnegie Mellon University.