Transparent combination of rule-based and data-driven approaches in speech understanding
نویسندگان
چکیده
We describe a domain-independent semantic interpretation architecture suitable for spoken dialogue systems, which uses a decision-list method to effect a transparent combination of rule-based and data-driven approaches. The architecture has been implemented and evaluated in the context of a mediumvocabulary command and control task.
منابع مشابه
A comparison between knowledge-driven fuzzy and data-driven artificial neural network approaches for prospecting porphyry Cu mineralization; a case study of Shahr-e-Babak area, Kerman Province, SE Iran
The study area, located in the southern section of the Central Iranian volcano–sedimentary complex, contains a large number of mineral deposits and occurrences which is currently facing a shortage of resources. Therefore, the prospecting potential areas in the deeper and peripheral spaces has become a high priority in this region. Different direct and indirect methods try to predict promising a...
متن کاملApplication of the rule extraction method to evaluate seismicity of Iran
Assessing seismic hazards involves specifying the likelihood, magnitude and location of earthquakes in a region. Predicting the seismic hazards is the first step in reducing the impact of the damage caused by an earthquake. In this study, to fully utilize all the known parameters which may possibly affect the occurrence of earthquakes (mb ≥ 4.5); a data-driven rule-extraction method called the...
متن کاملProposing a Novel Cost Sensitive Imbalanced Classification Method based on Hybrid of New Fuzzy Cost Assigning Approaches, Fuzzy Clustering and Evolutionary Algorithms
In this paper, a new hybrid methodology is introduced to design a cost-sensitive fuzzy rule-based classification system. A novel cost metric is proposed based on the combination of three different concepts: Entropy, Gini index and DKM criterion. In order to calculate the effective cost of patterns, a hybrid of fuzzy c-means clustering and particle swarm optimization algorithm is utilized. This ...
متن کاملBalancing data-driven and rule-based approaches in the context of a Multimodal Conversational System
Moderate-sized rule-based spoken language models for recognition and understanding are easy to develop and provide the ability to rapidly prototype conversational applications. However, scalability of such systems is a bottleneck due to the heavy cost of authoring and maintenance of rule sets and inevitable brittleness due to lack of coverage in the rule sets. In contrast, data-driven approache...
متن کاملData-Driven Approaches to Improve the Quality of Clinical Processes: A Systematic Review
Background: Considering the emergence of electronic health records and their related technologies, an increasing attention is paid to data driven approaches like machine learning, data mining, and process mining. The aim of this paper was to identify and classify these approaches to enhance the quality of clinical processes. Methods: In order to determine the knowledge related to the research ...
متن کامل