Topic Modeling and Figurative Language

Abstract

Located at the center of Jorie Graham’s collection The End of Beauty, “Self Portrait as Hurray and Delay” crafts a portrait of the artist, poised at a precarious moment in which thought begins to take shape. Like Penelope, Graham entertains the illusion, if only momentarily, of a choice between bringing a creative impulse into form or allowing it to come undone. A weaver of language, Graham subtly, deftly, but unsuccessfully attempts to delay the inevitable moment in poetic creation in which complexity of thought adopts form through language, and so realized is also reduced. In The End of Beauty, the beginning of the creative act signals an inevitable descent into meaning – language’s ultimate impulse. Understanding how topic modeling algorithms handle figurative language means allowing for a similar beautiful failure – not a failure of language, but a necessary inclination toward form that involves a diminishing of language’s possible meanings. However, the necessarily reductive methodology of sorting poetic language into relatively stable categories, as topic modeling suggests, yields precisely the kind of results that literary scholars might hope for – models of language that, having taken form, are at the same moment at odds with the laws of their creation. In the following article, I suggest that topic modeling poetry works, in part, because of its failures. Somewhere between the literary possibility held in a corpus of thousands of English-language poems and the computational rigor of Latent Dirichlet Allocation (LDA), there is an interpretive space that is as vital as the weaving and unraveling at Penelope’s loom.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 67 citations exist upstream.