Ars Electronica Archive
Prix
Prix Map
Pictures
Videos
Publications
Special Projects
Women in Media Art
Prix
The Prix Ars Electronica Archive is a collection enabling search and viewing of all the submissions since 1987. The award-winning projects are documented with catalogue texts and audio-visual media. All other submissions can be searched by title/artist and displayed with year, category in list form. Please cite the credits (artwork name, artist and photographer) and only use the materials if your article is related to Ars Electronica.
Compasses
Allison Parrish
Original: Compasses_courtesy_of_artist.jpeg (Compasses_courtesy_of_artist.jpeg) | 5760 * 5760px | 7.7 MB
Credits: Allison Parrish
Credits: Allison Parrish
Original: Compasses_credit_Elon_Schoeholz.jpg (Compasses_credit_Elon_Schoeholz.jpg) | 3000 * 3000px | 2.8 MB
Credits: Elon Schoeholz
Credits: Elon Schoeholz
Compasses is a collection of poems written with a machine learning model of spelling and phonetics. The model invents new words in negative spaces between supposedly discrete categories.
I trained a machine learning model with two parts: a “speller,” which spells words based on how they sound, and a “sounder-out,” which sounds out words based on how they're spelled. In the process of sounding out a word, the “sounder-out” produces a fixed-length numerical vector, known as a “hidden state,” which is essentially a condensed representation of a word's phonetics. The “speller” can then use the phonetic information contained in this hidden state to produce a plausible spelling of the word. The hidden state, like any other numerical vector, can be modified: translated, multiplied, blurred, averaged.
Each of the poems collected here results from a computer program I wrote that performs the following steps: (1) use the “sounder-out” to find the hidden state for a set of words, drawn from a hand-authored list (these are the words on the “points” of each poem); (2) find the vector halfway between the hidden state vectors for each pair of “point” words, and predict a plausible spelling for these halfway vectors with the “speller”; (3) find the vector of the midpoint of all eight vectors produced in (1) and (2), and likewise predict a plausible spelling for this vector.
The words from steps (1) and (2) are then programmatically arranged in the form of a compass rose. The word resulting from step (3) is placed in the middle. Compasses was first published as part of Andreas Bülhoff’s “sync” series.
Links: http://portfolio.decontextualize.com/#compasses
I trained a machine learning model with two parts: a “speller,” which spells words based on how they sound, and a “sounder-out,” which sounds out words based on how they're spelled. In the process of sounding out a word, the “sounder-out” produces a fixed-length numerical vector, known as a “hidden state,” which is essentially a condensed representation of a word's phonetics. The “speller” can then use the phonetic information contained in this hidden state to produce a plausible spelling of the word. The hidden state, like any other numerical vector, can be modified: translated, multiplied, blurred, averaged.
Each of the poems collected here results from a computer program I wrote that performs the following steps: (1) use the “sounder-out” to find the hidden state for a set of words, drawn from a hand-authored list (these are the words on the “points” of each poem); (2) find the vector halfway between the hidden state vectors for each pair of “point” words, and predict a plausible spelling for these halfway vectors with the “speller”; (3) find the vector of the midpoint of all eight vectors produced in (1) and (2), and likewise predict a plausible spelling for this vector.
The words from steps (1) and (2) are then programmatically arranged in the form of a compass rose. The word resulting from step (3) is placed in the middle. Compasses was first published as part of Andreas Bülhoff’s “sync” series.
Links: http://portfolio.decontextualize.com/#compasses
Author: Allison Parrish
Book design: Andreas Bülhoff
Book design: Andreas Bülhoff
Allison Parrish (US) is a computer programmer, poet, educator, and game designer whose teaching and practice address the unusual phenomena that blossom when language and computers meet. Named “Best Maker of Poetry Bots” by the Village Voice in 2016, Allison's computer-generated poetry has recently been published in BOMB Magazine and Nioques. Her first full-length book of computer-generated poetry, Articulations, was published by Counterpath in 2018. Allison is an Assistant Arts Professor at NYU's Interactive Telecommunications Program.