Ode to a Keatsian Turn: Creating Meaningful and Poetic Instances of Rhetorical Forms - Computational Creativity Research: Towards Creative Machines - page 195

anchor its understanding of these metaphors, and though these norms are very much
the stuff of banal clichés and stereotypes, such as that dogs chase cats and cops eat
donuts ,weshowhow Stereotrope finds and exploits corpus evidence to recast these
banalities as witty, incisive and poetic insights.
But Stereotrope cannot operate without knowledge. Samuel Johnson famously
opined that “ Knowledge is of two kinds. We know a subject ourselves, or we know
where we can find information upon it. ” Traditional approaches to the modeling of
metaphor and other figurative devices have typically sought to imbue computers with
the former (see [ 8 ]). More recently, however, the latter kind has gained traction, with
the use of the Web and text corpora to source large amounts of shallow knowledge
as it is needed (e.g. see [ 18 , 20 - 22 ]). But the kind of knowledge demanded by a
knowledge-hungry phenomenon such as metaphor is very different to the specialist
“book” knowledge so beloved of Johnson. Metaphor demands knowledge of the
quotidianworld that we all tacitly share but rarely articulate, not even in the thoughtful
definitions of Johnson's dictionary.
Fortunately, similes open a rare window onto our shared expectations of the world.
Thus, the as-as-similes “ as hot as an oven ”, “ as dry as sand ” and “ as tough as leather ”
illuminate the expected properties of these objects, while the like-similes “ crying like
a baby ”, “ singing like an angel ” and “ swearing like a sailor ” reflect intuitions of how
these familiar entities are tacitly expected to behave. The authors of [ 20 , 21 ] thus
harvest large numbers of as-as-similes from the Web to build a stereotypical model
of familiar ideas and their salient properties, while a similar approach is applied
(albeit on a smaller scale) by [ 16 ] using Google's query completion service. David
Fishelov [ 11 ] argues convincingly that poetic and non-poetic similes are crafted
from the same words and ideas. Poetic conceits use familiar ideas in non-obvious
combinations, often with the aim of creating semantic tension. The simile-based
model used here thus harvests almost 10,000 familiar stereotypes (drawing on a
stock of almost 8,000 features) from both as-as and like-similes. Poems construct
affective conceits, but as shown in [ 24 ], the features of a stereotype can be affectively
partitioned as needed into distinct pleasant and unpleasant perspectives. We are thus
confident that a stereotype-based model of common-sense knowledge is equal to the
task of generating and elaborating affective conceits for a poem.
Stereotrope 's model of common-sense knowledge requires both features and rela-
tions, with the latter showing howstereotypes relate to each other. It is not enough then
to know that cops are tough and gritty, or that donuts are sweet and soft; our stereo-
types of each should include the cliché that cops eat donuts ,justas dogs chew bones
and cats cough up fur-balls . Following [ 22 ], we acquire inter-stereotype relationships
from the Web, not by mining similes but by mining questions. As in [ 16 ], we target
query completions from a popular search service (Google), which offers a smaller,
public proxy for a larger, zealously-guarded search query log. We harvest questions
of the form “ WhydoXs

Ys ”, and assume that since each relationship
is presupposed by the question (so “ Why do bikers wear leathers ” presupposes that
everyone knows that bikers wear leathers), the triple of subject/relation/object cap-
tures a widely-held norm. In this way we harvest over 40,000 such norms from the
Web.

< relation >