1
Raymond Lau, Ronald Rosenfeld, Salim Roukos: Building scalable N-gram language models using maximum likelihood maximum entropy N-gram models. International Business Machines Corporation, Robert Tasinari, Sterne Kessler Goldstein & Fox, November 14, 1995: US05467425 (97 worldwide citation)

The present invention is an n-gram language modeler which significantly reduces the memory storage requirement and convergence time for language modelling systems and methods. The present invention aligns each n-gram with one of "n" number of non-intersecting classes. A count is determined for each ...


2
Raymond Lau, Ronald Rosenfeld, Salim Roukos: Building scalable n-gram language models using maximum likelihood maximum entropy n-gram models. International Business Machines Corporation, Robert Tasinari, Sterne Kessler Goldstein & Fox P L L C, June 17, 1997: US05640487 (66 worldwide citation)

The present invention is an n-gram language modeler which significantly reduces the memory storage requirement and convergence time for language modelling systems and methods. The present invention aligns each n-gram with one of "n" number of non-intersecting classes. A count is determined for each ...



Click the thumbnails below to visualize the patent trend.