High level knowledge sources in usable speech recognition systems
Communications of the ACM
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory
Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory
Pitch accent in context: predicting intonational prominence from text
Artificial Intelligence - Special volume on natural language processing
Integrating rules and connectionism for robust commonsense reasoning
Integrating rules and connectionism for robust commonsense reasoning
Statistical Language Learning
Hybrid Neural Network and Expert Systems
Hybrid Neural Network and Expert Systems
In-Depth Understanding: A Computer Model of Integrated Processing for Narrative Comprehension
In-Depth Understanding: A Computer Model of Integrated Processing for Narrative Comprehension
Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing
Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing
Integrating different learning approaches into a multilingual spoken language translation system
Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing
The TRAINS-95 Parsing System: A User''s Manual
The TRAINS-95 Parsing System: A User''s Manual
A speech-first model for repair detection and correction
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Some chart-based techniques for parsing ill-formed input
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
Detecting and correcting speech repairs
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Design of a hybrid deterministic parser
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 1
Learning dialog act processing
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
HLT '94 Proceedings of the workshop on Human Language Technology
Adaptive mixtures of local experts
Neural Computation
Parsing complex sentences with structured connectionist networks
Neural Computation
Knowledge Extraction from Transducer Neural Networks
Applied Intelligence
Neural Network Agents for Learning Semantic Text Classification
Information Retrieval
Integrating Linguistic Primitives in Learning Context-Dependent Representation
IEEE Transactions on Knowledge and Data Engineering
A Constructive Approach to Parsing with Neural Networks - The Hybrid Connectionist Parsing Method
AI '02 Proceedings of the 15th Conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence
Knowledge and Information Systems
Spoken language classification using hybrid classifier combination
International Journal of Hybrid Intelligent Systems
A novel evolutionary connectionist text summarizer (ECTS)
ASID'09 Proceedings of the 3rd international conference on Anti-Counterfeiting, security, and identification in communication
Hybrid preference machines based on inspiration from neuroscience
Cognitive Systems Research
Hi-index | 0.01 |
Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken-language systems still use a relatively brittle, hand-coded symbolic grammar or symbolic semantic component. In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a flat connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks. In order to test this approach, we have developed the screen system which is based on this new robust, learned and flat analysis. In this paper, we focus on a detailed description of screen's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the robustness under the influence of noisy or incomplete input. The main result of this paper is that flat representations allow more robust processing of spontaneous spoken language than deeply structured representations. In particular, we show how the fault-tolerance and learning capability of connectionist networks can support a flat analysis for providing more robust spoken-language processing within an overall hybrid symbolic/connectionist framework.