Table 2.
Corpus | NPs | Unique NPs | Unigrams | Unique Unigrams | Bigrams | Unique Bigrams | Trigrams | Unique Trigrams |
---|---|---|---|---|---|---|---|---|
Chest x-ray reports | 43,775 | 5,975 (14%) | 76,485 | 2,073 (3%) | 41,300 | 8,363 (20%) | 34,669 | 13,724 (40%) |
Discharge summaries | 93,919 | 19.790 (21%) | 135,203 | 8,549 (6%) | 72,866 | 28,592 (40%) | 71,513 | 41,369 (58%) |
Admission notes | 178,263 | 21,181 (12%) | 243,377 | 9,137 (4%) | 140,899 | 32,027 (23%) | 136,796 | 47,480 (35%) |