Sarah drew my attention to this -- Inger Christensen's book, Alphabet, built on / inspired by the fibonacci sequence, and reflections on translating it by her translator, Susanna Nied. The link in this text goes to one of the poems and its translation.
Translation notes on Genesis 1:1-3, along with a little Hebrew for non-Hebrews, some of the range of possibilities for each word/phrase, and some of the range of published translations. Eric, is this what you're looking for?
So NLTK via Python is about an interplay or conversation or convergence of two different languages -- a "natural one" (found in a corpus of text) and an invented one (Python) trying to speak to / process / extract things from the "natural" one -- translation in Steiner's predatory consume-the-object/hunted sense? and "processing" it into something consumable? But it sometimes seems more like a kind of viral invasion of a passive "host" ... Or the use / processing of a "natural" resource which seems more passive, like a timber forest (cf. Benjamin on "language forest").
In any case, insofar as this Natural Language Processing always involves a relationship between two languages -- a natural one and an artificial/invented one -- is it necessarily about translation? On the one hand, Python (and its user) does things with the corpus/body of the "natural" language in ways that remind me of Steiner and other predatory notions of translation. On another hand, it does nothing to it but makes things from copying or counting parts of it, producing readings of it in the process. On another another hand, I imagine it infiltrating the "natural" language corpus, circulating within its letters and spaces, nothing without its host, becoming something only when realized in its host ...?
This chapter is divided into sections that skip between two quite
different styles. In the "computing with language" sections we will
take on some linguistically motivated programming tasks without necessarily
explaining how they work
Here we will treat text as raw data for the programs we write,
programs that manipulate and analyze it in a variety of interesting ways.
But before we can do this, we have to get started with the Python interpreter.