Introduction | Building a $k$-gram language model | Step 1: Loading the training corpus | Step 2: preprocessing and tokenizing sentences | Step 3: get $k$-gram frequency counts | Step 4. Build the final language model | Using language_model objects | Word continuation and sentence probabilities | Generating random text | Compute language model's perplexities | Conclusions | References

Features | Performance tests | Key insertion | Key query | Key deletion | Conclusions

Introduction | Basic Manipulations | Sets | Key and value types | Setting default values | Using custom key comparison and hash functions