作者: M. Epstein , K. Papineni , S. Roukos , T. Ward , S. Della Pietra
DOI: 10.1109/ICASSP.1996.540319
关键词:
摘要: We present a new approach to natural language understanding (NLU) based on the source-channel paradigm, and apply it ARPA's Air Travel Information Service (ATIS) domain. The model uses techniques similar those used by IBM in statistical machine translation. parameters are trained using exact match algorithm; hierarchy of models is facilitate bootstrapping more complex from simpler models.