[Humanist] 29.502 tools to analyze poetry

Humanist Discussion Group willard.mccarty at mccarty.org.uk
Wed Nov 25 09:19:33 CET 2015


                 Humanist Discussion Group, Vol. 29, No. 502.
            Department of Digital Humanities, King's College London
                       www.digitalhumanities.org/humanist
                Submit to: humanist at lists.digitalhumanities.org

  [1]   From:    "Koolen, Corina" <C.W.Koolen at uva.nl>                       (8)
        Subject: RE:  29.496 tools to analyze poetry

  [2]   From:    Ryan James Heuser <heuser at stanford.edu>                   (10)
        Subject: Re:  29.496 tools to analyze poetry

  [3]   From:    margento <margento.official at gmail.com>                    (40)
        Subject: 29.496 tools to analyze poetry (Humanist Discussion Group)


--[1]------------------------------------------------------------------------
        Date: Tue, 24 Nov 2015 12:07:15 +0000
        From: "Koolen, Corina" <C.W.Koolen at uva.nl>
        Subject: RE:  29.496 tools to analyze poetry
        In-Reply-To: <20151124090222.AD4AF6FA6 at digitalhumanities.org>


Dear Avraham,

Last may Nina McCurdy presented an impressive paper at the NAACL workshop Computational Linguistics for Literature, with a tool that analyses a wide range of rhyme devices in poetry. It was developed with the help of actual potential users. I'm not sure if the tool is readily available, but the paper was called 'A Formalism for Analyzing Sonic Devices in Poetry', perhaps you could contact her?   

All best,

Corina Koolen

PhD candidate Digital Humanities
Institute for Logic, Language and Computation
University of Amsterdam
www.corinakoolen.nl 



--[2]------------------------------------------------------------------------
        Date: Tue, 24 Nov 2015 20:07:52 +0000
        From: Ryan James Heuser <heuser at stanford.edu>
        Subject: Re:  29.496 tools to analyze poetry
        In-Reply-To: <20151124090222.AD4AF6FA6 at digitalhumanities.org>


Dear Avraham, Humanist members,

I want to mention that the Stanford Literary Lab has an ongoing project developing software for the automatic annotation of poetic formal features -- so far, stanzaic and metrical forms (not rhyme) -- from plain text. The project involves myself, along with Mark Algee-Hewitt, Maria Kraxenberger, J.D. Porter, Jonathan Sensenbaugh, and Justin Tackett. The metrical parser was written by me and linguists Josh Falk and Prof. Arto Anttila. [I mention these names so as to give credit to all the people who have worked very hard and creatively on the software and project.]

We presented the project at DH2014 in Lausanne, and are currently working on drafting it up as an article for submission to a journal. But, I also maintain a Github repository of major milestones of the code as the project progresses, available here:

https://github.com/quadrismegistus/litlab-poetry

It's written in Python, and there are some (minimal) instructions on how to use it. But do feel free to contact me if you decide to use it and have any questions.

All this said, I do want to echo Laura Mandell's caution that metrical scansion is a very tricky affair, with people (including those of us on the project!) often disagreeing about the "right" parse. We've circumvented this problem by (a) trying to characterize the central metrical tendencies of the poem as a whole rather than a line-by-line analysis, and (b) relying on the standard issue DH argument that what computation provides is less correctness than consistency, making possible a comparison across poems, genres, or periods by virtue of the method remaining computationally constant.

Hope this is useful! peace,

Ryan Heuser
Ph.D. Candidate in English, Stanford
http://ryanheuser.org | @quadrismegistus



--[3]------------------------------------------------------------------------
        Date: Tue, 24 Nov 2015 15:32:14 -0500
        From: margento <margento.official at gmail.com>
        Subject: 29.496 tools to analyze poetry (Humanist Discussion Group)
        In-Reply-To: <20151124090222.AD4AF6FA6 at digitalhumanities.org>


Hi Abraham and all,

Me and my team have worked in digital poetry analysis for a couple of years
now, have published a paper on multilable subject-based classification of
poetry and more recently have submitted (together with my team) a paper on
meter and rhyme to a DH journal and one on meter only to an artificial
intelligence conference (FLAIRS, where we presented the poetry subject
classification paper last year, here is the link
http://webcache.googleusercontent.com/search?q=cache:7COEISzFQPUJ:www.aaai.org/ocs/index.php/FLAIRS/FLAIRS15/paper/download/10372/10322+&cd=2&hl=en&ct=clnk&gl=ca
).

Here is also the abstract of the forthcoming meter and rhyme paper:

Poetry Classification by Meter and Rhyme as Part of the Graph Poem Project

MARGENTO (Chris Tanasescu)margento.official at gmail.com

Bryan Paget
bdjpaget at gmail.com

Diana Inkpen
diana.inkpen at uottawa.ca
University of Ottawa
August 25, 2015

Abstract:

This paper presents a brief introduction to the the Graph Poem project,
which promises a novel approach for analyzing large corpora of poetry. By
treating poems and their shared features as nodes and edges of a graph, we
can study previously unknown relationships. To this end, we repurposed an
open source poetry scanning program (the Scandroid by Charles O. Hartman) as
a feature extractor for poetic meter and incorporated it into our machine
learning workflow. We also made our own rhyme detector using the Carnegie
Melon University Pronouncing Dictionary as our primary source of
pronunciation information. Initial work already shows a useful ability to
classify poems by use of poetic meter and rhyme. Future work will involve
assembling the graph depicting the interconnected nature of poetry (and
perhaps human thought in general) across history, geography, genre, etc.

Keywords: Machine learning, digital humanities, poetry

We also have a project websitehttp://artsites.uottawa.ca/margento/en/the-graph-poem/  at uOttawa.

Please let me know if you want to know more about the tools we've developed.

All best,

*MARGENTO*
http://artsites.uottawa.ca/margento/en
www.asymptotejournal.com/
http://christanasescu.blogspot.com/






More information about the Humanist mailing list