Monthly Archives: June 2019

Computation and Rhetorical Invention: Finding Things to Say With word2vec

Is it possible to make a sonnet based on a theme without having to attend simultaneously to form? Can one focus on inventio to generate a poem and leave much of the elocutio to algorithms?

Below is a web prototype for generating sonnets in French, English or Spanish using verses from the Théâtre Classique‘s collection of plays, Allison Parish’s compilation of poetry from Project Gutenberg, or the Corpus of Spanish Golden-Age Sonnets. The code, available here, makes use of natural language processing tools to enable a user to invent (in the rhetorical sense of finding things to say with language) a sonnet with an initial verse and a pair of words as the basis of an analogy using word2vec. For now the initial verse is selected with a quick word search against the corpus, and only the first 50 random verses that match the query are retrieved (if there are 50 or less verses that match the query, all of them are retrieved). The pair of words can be anything in the corpus, and while terms such as femme and homme establish a clear binary opposition with the same part of speech, any two words can be used. The pair serves as the basis of an analogy (one of Aristotle’s topoi for rhetorical invention) for systematically transforming a verse, word by word. The procedure (explained more fully in the code repo) takes a verse, modifies it by analogy, finds another verse in the corpus that most closely matches the transformed verse and adheres to a specific rhyme scheme for sonnets (abba abba ccd eed, with alternating masculine and feminine rhymes in French), and repeats the process until 14 verses are selected.

Go ahead and generate a sonnet, using the defaults if you wish, and see what happens:

You may invent imperfect sonnets with the generator. All the verses in French should be alexandrines, and those in English pentameters, but sometimes the rhymes are off, either because the same rhyming word is used repeatedly or two words that are supposed to rhyme do not. This is a bug I am working on.

You will notice that if you move the pointer over a verse, green italicized text will appear. This text is the result of transforming the verse by the analogy based on the pair of words. In this way you can begin to infer how each verse was selected from the corpus to generate the sonnet. If you supply other words as parameters, you can find verses with different analogies.

Another recently added feature is the ability to edit the last verse selected. The code attempts to verify that the edited verse complies with the defined rules for rhyme and scansion for this particular kind of sonnet, and if the edited verse does not comply, it is rejected and the original verse is restored.

The idea for selecting verses from other poems in order to assemble a new poem is not new. As early as the third or fourth century C.E. authors were recycling verses from Virgil in a form identified by Ausonius as the cento.

This is very much alpha code. It may be possible to produce an interesting sonnet, but what I find interesting in this project is the way one can model a particular approach to inventing poetry to observe how tools usually deployed for computational analysis (word embeddings, tf-idf vectors, phonetic transliteration) can contribute to creative synthesis.