Tag: ekphrastic

Co-authored Ekphrastic Poem

Shuffled frequencies:

Say something specific but utterly preposterous
Use a word (slang?) you’ve never seen in a poem
Use the proper name of a person and the proper name of a place
Use a piece of false cause and effect logic
Make a declarative assertion that sounds convincing but finally makes no sense.
Use a piece of “talk” you’ve actually heard (preferably in dialect and/or which you don’t understand)
Make the persona in the poem do something that they could not do in “real life.”
Modify a noun with an unlikely adjective.
Write in the future tense, such that part of the poem seems to be a prediction.
Use a metaphor.
Use a phrase from a language other than English.

Source:

Imagine swallowing the moon, sun, land and sea in one violent gulp, reverberating waves
slinking and sticking like teardrops around what once was everything and nothing, drowning life,

reversing genesis, spilling into that unchartered void and filling what’s empty with sacred
emptiness. Miniscule droplets reflecting hues of yellow and orange, distorting the world behind

them, elongating, squishing, creating new images from the old. A unique world within each
droplet. Steve once said “we contain god within ourself”. Water from loch 9, West Glenville.

I got to be god of that small summer. From water came the world, pushed in pulses of flowing
earth. From flux the sphere took shape and knew itself, became aware of origin calling it a

knowledge. At the third position, light sheens through, calls a question with a gargle and spills
us upon a floor. Popped latex isn’t biodegradable even if you can recycle the picture from

Facebook to Twitter to Instagram. Quit bursting pollutants when there are thirsting
people–instead balloon filters, clean our water. I can’t drink likes no matter how they flow.

I hate to burst your bubble but you’re not going to make any money doing that. Thanks, but that
bubble already popped and I’ve been having the greatest time drowning in its dislocated

droplets. I hold the orb still with my mind, against the spray and watch the water run over it
and drip off, sunset glowing through. I do not let it sway. Wonder if this is how God feels about

the sun, the moon, the earth, letting each single droplet drip where it may, but not letting it
waiver. Moons aquatic // nebulas the mind // wet & never drowned // breath, blue-orange

paradise // and the eye is all sandy horizon. There will be more things breaking: the light
through winter sea. This egg of ice will flood and shatter, will spill yellow, pale at first, and paler.

It’s raining and the hammer drops in pieces. A dizzy background, something’s focused: in this
droplet is the sunburst. Where we fall is no man’s land for our orb of yellow but for the

one-two-three seconds before we dissolve into a purple-black, we’ll be the epicenter of a ray,
a bedizened heat, until we—ca pika shiu—pool endlessly. For a moment, liquefied silence, bursting. 

 

by Jessica Melendy, Westley Smith, Jaime Chernoch, Nick Snow, Kieran Moriarty, Jessamyn Wolff, Megan Waring, Shannon Kafka, Christie Towers, Nick Trefonides, Krisela Karaja, Sabina Lindsey

Related Work

From Visual Storytelling (Huang et al. 2016):

“Abstract: We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND1 v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.”

Visual Storytelling (Huang et al. 2016) builds off of related work in vision to language that examined “image captioning  (Lin et al., 2014; Karpathy and Fei-Fei, 2015; Vinyals et al., 2015; Xu et al., 2015; Chen et al., 2015; Young et al., 2014; Elliott and Keller, 2013), question answering (Antol et al., 2015; Ren et al., 2015; Gao et al., 2015; Malinowski and Fritz, 2014), visual phrases (Sadeghi and Farhadi, 2011), video understanding (Ramanathan et al., 2013), and visual concepts (Krishna et al., 2016; Fang et al., 2015)” to progress from literal description to narration. But realistic storytelling is not the only aspect of human intelligence.

The crowd-sourcing methods for the Cooperative Poem (CoPo) project are similar to the methods outlined in Visual Storytelling, and along with generating a collection of co-authored poems, the CoPo dataset can also be analyzed to inform an AI model of ekphrastic human expression.

According to the Poetry Foundation, ekphrastic poetry is “a vivid description of a scene or, more commonly, a work of art. Through the imaginative act of narrating and reflecting on the ‘action’ of a painting or sculpture, the poet may amplify and expand its meaning.” The expansion of meaning occurs because we are capable of more than narrating a visual scene. Our ability to reflect on the past, present, and future implications of a visual scene, and its associated narrative, allows our imagination to create a unique narrative.

 

Political Applications of Ekphrastic Poetry

Respond to statements made by public officials. In the demonstration above, I’ve used tweets made by President Trump. There are project prompts that appear above the tweet and a form field below for users to enter one line of poetry or more. In the above example, there are 200 possible combinations of project prompt and trump tweet.

In the future, instead of using trump tweets that have occurred in the past, I will include videos and quotes of recent controversial statements made by government officials. The project prompts will be unbiased. Use poetry to engage in political conversation.

The many poetic and political conversations can be combined using an algorithm into large response poems to each of the government officials. These response poems are an unofficial average of community response.

Regarding predicting the outcome of an election, this could act as an alternative to traditional polling.

CoPo (Cooperative Poem) Mobile Application

I do not often sit down at my desk with a journal to deliberately write poems. More often than not, lines of poetry occur to me spontaneously when I’m on-the-go. Here is my essential question: how can a mobile application that randomly prompts users to input one line of poetry per day make the long-timescale process of writing a collection of poems based-on several prompts more efficient?

The python code that automates the order of the Twenty Little Poetry Projects would be one prompt in the back-end of the mobile application. The front-end of the mobile application would have a form that collects user completions of little poetry projects. There will be other prompts along with Twenty Little Poetry Projects in the back-end of the application that celebrate inventiveness and juxtaposition. The front-end of the mobile application would randomly notify the user to complete a random project from any of the several prompts in the back-end. Users must complete the project in one line of poetry or more.

Everyone who downloads the mobile application and signs-up for CoPo (cooperative poem) becomes a member and agrees to complete a project randomly once per day. CoPo is free to sign-up, but private. Only members can invite other people to become members. All members will be co-authors of the randomly generated collection of poems at the end of a year.

Users can open the application at any time to complete a project, read poems that were generated from the input of all members, or participate in discussion with other members. The source code for the back-end of the application that decides the poetic form and project prompts would be viewable to all users. Users can make suggestions to improve the source code in the discussion board.

The author of Virtual Muse, Charles G. Hartman, used a computer to explore the “effects of randomness, arbitrariness, and contingency on poetic composition.” This project is also an experiment with computer poetry, but unlike Hartman’s experiments, this project is interested in exploring the long-timescale benefits of using a computer to assist an organized group in the creation of a collection of poetry line-by-line.  

CoPo would facilitate the combination of poetic minds. The application would decide the chronology of the agreed-upon and predictable (in form, not content) creative process, and therefore the poets can focus on imagery. Two or more poets will be able to write the same poem simultaneously, and they will be able to complete a collection of poems without pencil, pad, and pandemonium.

If this mobile application were publicly available and widely used, then there are other possibilities for its use beyond writing a collection of inventive poems. Instead of being randomly notified to only complete a project (For example, “Write a question?” and “Say something specific but utterly preposterous”), users could have to complete the project ekphrastically, within the context of a song or an image. User project-completions would be associated with the art that it was ekphrastically written from, and by better understanding that association and creating an algorithm that takes an average of human response to art, we may better understand how to create an artificially intelligent algorithm that has “feelings” and “memory” by randomly generating responses to art and collecting data on itself continually.

© 2024 Tref's Travels

Theme by Anders NorenUp ↑

Skip to toolbar