natural language processing

Short description

This workshop presents a hands-on introduction to the RiTa v2.0 tools, including the new RiScript language. Version 2 of RiTa is a complete rewrite of the library that is easier-to-use, faster and more powerful. The workshop will cover the basics of RiTa and RiScript in JavaScript, with a specific focus on the Observable notebook environment. The number of addition topics covered, and the depth to which they are explored, will vary in relation to the time allotted by conference organizers and the experience of participants. While no specific skills are required for participation, familiarity with JavaScript and a basic knowledge of programming concepts (conditionals, variables, loops, etc.) will be assumed.

Record Status
Description (in English)

To Pray Without Ceasing is a web app that autonomously prays for people. It searches Twitter for expressions of need (e.g. "I need somebody to hug me right now" or "I need more money in my bank acct wtf"), especially those tweeted by users who have few followers and who are perhaps in need of solicitude. It then issues prayers for them using a variety of NLP techniques. Visitors to To Pray Without Ceasing must activate the system's prayers in a simple but symbolically significant way: they must light a candle (while making sure not to move the cursor too fast; one must proceed mindfully in sacred space). The action of lighting a candle is designed to make the system not "interactive" but rather what Robert Pfaller would call "interpassive"; the visitor delegates the work of praying---the practice of religion itself---to the machine, yet she still can feel vaguely responsible for whatever good work it does, whatever good words it utters. The system prays in different ways over the course of 24 hours, evoking the "Liturgy of the Hours" ("Horae Canonicae"). After 24 hours the sequence begins again, praying for a new batch of needs discovered on Twitter from the previous day. Thus the humble and pious work of paying attention to the needs of strangers is never finished.

Multimedia
Remote video URL
Content type
Author
Year
Language
Publication Type
Record Status
Description (in English)

As N. Katherine Hayles has argued, the proliferation of digital media has radically transformed the ways in which we pay attention, privileging a kind of frantic and promiscuous “hyper attention” over the sustained “deep attention” traditionally solicited by long-form print media. “Fragile Pulse: A Meditation App” invites the reader to consider the ways that computational media may indeed cause what has been called “digital distraction” but may also be used in the context of regimes of self-care and self-quantification to increase our capacity to pay attention deeply. While tools for measuring, testing, and training for one's body and mind are widely popular (from the Fitbit to meditation apps like Headspace), the theme of self-care is generally peripheral to the electronic literature community. “Fragile Pulse” takes the form of a digital text/web application that encourages the viewer to pay attention to attention. Using data from the webcam and microphone, it quantifies the reader's bodily stillness and quietness. When the reader is still and quiet, a calmly pulsating text unfolds on the screen, guiding the reader through a meditation. However, when the program detects movement or noise above a certain threshold, signaling distraction, the screen becomes filled with “stray thoughts” generated on-the-fly via a natural language processing. Visually, these stray thoughts (shards of hyper attention) cover up the meditative text, blinking and wiggling to further emphasize their status as distractions. Echoing the way that digital/social media can foster anxiety and depression, this text generation system models the way a mind can slip from harmless distractions to anxious obsessions. Only the viewer's silence and stillness dispel these computer-generated distractions and re-launch the human-authored meditative text. This piece thus raises questions not only about attention but also about the ways that digital technologies of self-care enforce regimes of (sometimes extreme) cognitive and physical discipline.

Hayles, N. K. (2007). Hyper and deep attention: The generational divide in cognitive modes. Profession, 2007(1), 187-199.

http://www.computationalcreativity.net/iccc2019/assets/creative-submissions/iccc19-booten-fragile-pulse.pdf

By Johannah Rodgers, 30 October, 2015
Publication Type
Language
Year
Record Status
Abstract (in English)

This thesis explores how various computer programs
construct poems and addresses the way several critics
respond to these computer generated texts. Surprisingly,
little attention has heretofore been paid to these programs.
Critics who have given the matter attention usually focus on
only one of the myriad programs available, and more often
than not, such scholarship concludes with a disparagement of
all such projects. My work reexamines computer generated
poetry on a larger scale than previously exists, positing
some conclusions about how these texts affect contemporary
theories of authorship and poetic meaning.
My first chapter explicates the historical debate over the
use and limits of technology in the generation of text,
studying similitudes between certain artistic movements and
computer poetry. This historical background reveals that
the concept of mechanically generated text is nothing new.
My second chapter delineates how the two main families of
computer poetry programs actually create these texts.
Computer programs combine existing input text, aleatory
functions, and semantic catalogues, which provides insight
into how humans both create and interact with these
programs. At the same time, this study illustrates the
difficulty in defining the level of intention and influence
by individuals on the textual product, and therefore these
texts challenge our traditional notions of authorship and
the value of poetry. My third and final chapter argues that
contemporary literary theory and poetics creates the
conditions under which computer generated poetry can pose as
a human product. The success of these programs to deceive
readers about the origins of the text becomes clearer with
the results of a survey I conducted in which the respondents
were fooled by the machine more often than not. This
possibility of machine-created text masquerading as human
art threatens many critics, who quickly dismiss the process
and its results as non-poetic, but I conclude that since the
computer complicates foreknowledge of origin in some
contemporary poetic forms, this intrusion by the machine
prompts us to reconsider how we traditionally value and
interpret poetry.

Description in original language
Abstract (in original language)

See above.

Pull Quotes

"Formulaic poetry generating programs produce texts
influenced by two individuals : the programmer and the
operator. One could argue that they are one in the same,
since by inputting data such as subject and gender, the
operator enters into the role of programmer and "finishes"
the instruction set. It would follow that in such a case,
the label "programmer" now applies to a role and not to a
specific individual. Much to the possible disappointment of
the Bill Chamberlains and Chris Westburys of the programming
world, authorship now disintegrates into a true author
"function," not applicable to identifiable individuals. Yet
somehow this creates a nagging sense of inaccuracy precisely
because of the type of language computer programmers use."

Content type
Year
Language
Platform/Software
License
GPL
Record Status
Description (in English)

The Cabinet Noir was the name given in France for the secret office where the post of suspected persons was opened and inspected before being forwarded to its final recipient. Governments since have used similar Black Chambers to spy on their populations communication via telegram, telephone and internet media. In order to avoid detection, some individuals have resorted to the technique of Steganography, where communications are hidden in seemingly innocent messages. This can lead to a state of paranoia where every text may contain evidence of nefarious intentions. This work takes the email exchange and data produced for the WEISE7 Labor exhibition and mixes it with the text of Edgar Allan Poe's detective story The Purloined Letter. The result is a paranoid archive of implied subtext.

Screen shots
Image
Image
By Scott Rettberg, 21 May, 2011
Publication Type
Language
Year
Record Status
Abstract (in English)

Harger's interview with Mateas and Stern focuses on the development of theiir conception of interactive drama and the Façade project.

Pull Quotes

To be interactive drama, an experience should have rich, emotive, socially-present characters to interact with, and a strong sense of story progression that is organically and dynamically shaped by the player's interaction.

To keep things minimal, from both an aesthetic as well technical perspective, we wanted to find a scenario that would have the least number of characters while still delving deeply into issues about people's inner lives. It's amazing the scarcity of satisfying interactive experiences that are actually about people's lives--subject matter that is, of course, the heart of the best literature, cinema, theater and television.

Attachment
File
Creative Works referenced
Description (in English)

Eliza (Weizenbaum 1966) is the first chatterbot -- a computer program that mimics human conversation. In only about 200 lines of computer code, Eliza models the behavior of a psychiatrist (or, more specifically, the "active listening" strategies of a touchy-feely 1960s Rogerian therapist).

(Source: Dennis G. Jerz's site)