There are two kinds of literature to review: (I) other poetry-generation
systems, regardless of their stragety; (II) more general NLG or MT systems that
use and/or learn templates. Also important is (III) evaluation of results.

SUMMARY: No one seems to be doing what I am.

I. Other poetry-generation systems

SUMMARY: other poetry-generation systems exist; but all the ones I found seem
to rely heavily on manually-created rules and lexica.

Manurung, Graeme Ritchie, Henry Thompson. (2000). Towards A Computational Model
of Poetry Generation.  http://citeseer.ist.psu.edu/manurung00towards.html

Uses an evolutionary algorithm (stochastic hill climbing search) to find the
best poem. They evaluate candates based on their rhythm; they mutate them using
a ``semantic explorer'', a ``semantic realizer'', and a ``syntactic
paraphraser''. They use hand-crafted grammar and lexicon to do all this,
however.

Manurung. (2003). An evolutionary algorithm approach to poetry generation.
(Ph.D. thesis).

Continues the above. Includes lots of relevant discussions. Mentions several
even earlier systems dating back to at least 1974.

Gerv\'as. (2000). An Expert System for the Composition of Formal Spanish
Poetry.
and
Gerv\'as. (2000). WASP: Evaluation of Different Strategies for the Automatic
Generation of Spanish Verse

Uses a rule-based system to generate Spanish poetry. The rules were manually
made by reviewing academic literature on poetry.

II. General NLG/MT templates and systems that learn templates

SUMMARY: People have been learning templates from corpora. No one seems to have
just calculated idf and cutoff; this is probably because MT (as well as NLG)
have more than poetry, so one needs to know more about which templates are
appropriate when.

Lu, Zhou, Li, Huang, and Zhao. (2001). Automatic Translation Template
Acquisition Based on Bilingual Structure Alignment.

Use aligned bilingual corpus + LM to extract templates for translation.

McTait. (2001). Linguistic Knowledge and Complexity in an EBMT System Based on
Translation Patterns.

Extracts sentences from bilingual corpus that are translations of each other.

Carl. (1999). Inducing Translation Templates for Example-Based Machine
Translation.

Extracts more complicated, general templates from bilingual corpus.

Deemter, Krahmer, and Theune. (2004). Real vs. template-based natural language
generation: a false opposition?
http://www.csd.abdn.ac.uk/~kvdeemte/mock-rae-2004/templates-squib-8pages.pdf

Argues that the line between template-based NLG systems and "real" NLG systems
(where every word is allowed to vary) is blurry.

III. Evaluation

Gerv\'as. (2002). Exploring Quantitative Evaluations of the Creativity of
Automatic Poets

Develops evaluation metrics for poetry.

Pease, Winterstein, and Colton. (2001). Evaluating Machine Creativity.

Distinguish between the process and the results, among other things.

Ritchie. (2001). Assessing Creativity.

What makes a program creative?