But you run (or take) the risk that your results are merely tentative
Unless you base your corpus on a sample representative!Don’t try a demonstration,
Just register your name.
If not “I saw, I conquered”
You can always say “ICAME”.But if you feel constrained to have your grammar realistical,
Your particles based properly, your lexis authentistical,
Don’t rely on introspection, on the magic and the mystical,
Don’t hope to find a software pack of strategies heuristical,
Just build yourself a corpus (or some corpora) statistical!
Excerpt from How to Dispose of the Body, or The Corpus-Maker’s (Di-)Lemma by Anna Kerr-Luther
In other words, yes, it’s a whole poem about corpus linguistics. ICAME, for reference, is the International Computer Archive of Modern and Medieval English.
(via allthingslinguistic)