Brill Tagging

Consider the following sentence:

Most likely tags: And\CC so\IN the\DT die\VB was\VBD cast\VB.

Correct likely tags: And\CC so\IN the\DT die\NN was\VBD cast\VB.

Instantiate each of Brills templates for the before or preceding cases given this data to generate 6 transformations (that is, do not instantiate templates using following or after).

Considering Examples 5.4-5.6 in the book, which of these transformations do you think will be most effective on a large corpus, and why?