Statistics of different n-grams on the Brown corpus
length
perc_total_nobreaks
avg_words_per_sent
avg_breaks_per_sent
breaks_per_word
2
0.02
20.3452
13.3255
0.65
3
0.07
22.636
7.819
0.34
4
0.30
28.86
2.872
0.09
5
0.76
28.878
0.708
0.02