Soft computing-based approach for natural language call routing systems
Sameeh Ullah, Fakhri Karray, Arash Abghari, Sushil Kumar Podder · 2007
Call routing based on Natural Language Understanding remains a complex and challenging research area in machine intelligence and language understanding. This is despite the apparent limited success of a few commercial natural language call routing systems. This challenge is due to the limitations imposed by the speech recognition engine, the language model, and the natural language parser. In this paper, we propose a system to enhance the performance of automated call routing applications based on knowledge-based networks. The main focus of this paper is on the enhancement of the performance at the Natural Language Understanding level. We investigate soft computing techniques such as Learning Vector Quantization and the Genetic Algorithm. We find that the Genetic Algorithm outperforms Learning Vector Quantization. We achieve an accuracy rate of 84.12% using the Genetic Algorithm vs. 73% for Learning Vector Quantization.