ARPA language model documentation

There is actually not much more to say about the format than is said in those docs..

Besides, you'll probably want to prepare a text file with sample sentences and generate the language file based on it. There is an online version which can do it for you: lmtool

You can complement those docs with this tech report that gives a comprehensive overview of smoothing for language modeling: http://www.ee.columbia.edu/~stanchen/papers/h015a-techreport.pdf You will also find definitions for backoff models and interpolated models.