Rico Sennrich et al. quantified in their 2016 paper "Neural Machine Translation of Rare Words with Subword Units": on a 100-million-word German corpus, keeping whole words requires a vocabulary of 1.75 million entries, and the test set still leaves 1,079 unknown words; splitting into characters requires about 3,000 symbols, but the corpus balloons to 550 million positions; the subword method BPE uses about 63,000 symbols, 112 million positions, and zero unknown words.