SCREEN Symbolic Connectionist Robust EnterprisE for Natural language

PROJECT - DESIGN/SPECIFICATION:

Volker Weber and Stefan Wermter

STUDENTS:

Stefanie Haack, Matthias Löchel, Manuela Meurer, Ulf Sauerland, Marcus Schrattenholzer

PROJECT-DESCRIPTION:

SCREEN is a new approach of a system for fault-tolerant speech parsing. Speech parsing describes the syntactic and semantic analysis of spontaneous spoken language. The general approach is based on incremental flat analysis, learning of syntactic and semantic speech parsing, parallel integration of current hypotheses, and the consideration of various forms of speech related errors. The goal for this approach is to explore the parallel interactions between various knowledge sources for learning incremental fault-tolerant speech parsing. This approach is examined in the system SCREEN using various hybrid connectionist techniques. Hybrid connectionist techniques are examined because of their promising properties of inherent fault tolerance, learning, gradedness and parallel constraint integration. The input for SCREEN is hypotheses about recognized words of a spoken utterance potentially analyzed by a speech system, the output is hypotheses on the general approach, the overall architecture, and examples for learning flat syntactic speech parsing. Different from most other speech language architectures SCREEN emphasizes an interactive rather than an autonomous position, learning rather than encoding, flat analysis rather than in-depth analysis, and fault-tolerant processing of phonetic and semantic knowledge.

CURRENT PUBLICATIONS:

[Amtrup/Hauenstein/Pyka/Weber/Wermter 1994]
Jan Willers Amtrup; Andreas Hauenstein; Claudius Pyka; Volker Weber, Stefan Wermter. An outline of the Verbmobil project with focus on the work at the University of Hamburg. In P. Mc Kevitt, editor, Proceedings of the AAAI-94 Workshop on Integration of Natural Language and Speech Processing. (Seattle, Washington, USA), August 1994.
[Weber/Wermter 1995a]
Weber, Volker, Wermter, Stefan. Towards Learning Semantics of Spontaneous Dialog Utterances in a Hybrid Framework. In J. Hallam, editor, Hybrid Problems, Hybrid Solutions, pp. 229-238, (Sheffield, UK), IOS Press: Amsterdam, April 1995.
[Weber/Wermter 1996a]
Weber, Volker, Wermter, Stefan. Using hybrid connectionist learning for speech/language analysis. In Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing, pp. 87-101, Springer Verlag: Berlin, March 1996.
[Weber/Wermter 1996b]
Weber, Volker, Wermter, Stefan. Artificial Neural Networks for Repairing Language. In Proceedings of the 8th International Conference on Neural Networks and their Applications (NEURAP'95/96), pp. 117-123, (Marseille, FRA), March 1996.
[Wermter/Weber 1994a]
Wermter, Stefan, Weber, Volker. Learning fault-tolerant speech parsing with SCREEN. In Twelfth National Conference on Artificial Intelligence (AAAI-94). pp. 670-675, Seattle, Washington, July/August 1994.
[Wermter/Weber 1994b]
Wermter, Stefan, Weber, Volker, Learning fault-tolerant speech parsing with SCREEN. Verbmobil-Report 16, University of Hamburg, Computer Science Department, Natural Language Systems Division, Hamburg, FRG, Juni 1994.
[Wermter/Weber 1996]
Wermter, Stefan, Weber, Volker. Artificial Neural Networks for Automatic Knowledge Acquisition in Multiple Real--World Langauge Domains. In Proceedings of the 8th International Conference on Neural Networks and their Applications (NEURAP'95/96), (Marseille, FRA), March 1996.
[Wermter/Weber 1996a]
Wermter, Stefan, Weber, Volker. Interactive Spoken-Language Processing in a Hybrid Connectionist System. In IEEE Computer - Theme Issue on Interactive Natural Language Processing, volume 6, no. 7, pp. 65-74, July 1996.
[Wermter/Weber 1996b]
Wermter, Stefan, Weber, Volker. Spoken Language Processing in the Hybrid Connectionist Architecture SCREEN. Verbmobil-Report 138, University of Hamburg, Computer Science Department, Natural Language Systems Division, Hamburg, FRG, July, 1996.
[Wermter/Weber 1997]
Wermter, Stefan, Weber, Volker. SCREEN: Learning a Flat Syntactic and Semantic Spontaneous Language Analysis using Artificial Neural Networks. In Journal of Artificial Intelligence Research, volume 6, pp. 35-85, 1997.