Language modeling for content extraction in human-computer dialogues
Wolfgang Reichl, Bob Carpenter, Jennifer Chu‐Carroll, Wu Chou · 1998
In this paper we discuss the role of language modeling in a novel natural language dialogue system designed to automatically route incoming customer calls. We arrive at two significant conclusions: First, standard word error rate measures do not reflect application specific requirements; highly reliable content extraction is possible with relatively high word error rates. Secondly blending human-human data with human-machine data did not improve the performance in language modeling. 1.