Over at Jim Carpenter's blog, he has a series building on why aesthetic language generation (ALG) is difficult. There are plenty of discussions on the nature of working with aesthetic text generation systems from a writer/reader perspective, but very little on the challenges and questions raised in the actual construction of these systems (outside of the purely technical discussions within fields like Computational Linguistics). Jim has constructed a large scale electronic text composition system entitled "Erica T. Carter" and knows first hand the issues involved. Anyone interested in this area should keep an eye on his posts.

The performance at the Vancouver Art Gallery Friday on Oct 28, 2005 was great. I was a bit nervous from the rehersal the night before. I had incorporated the rhyming code i’ve been working on into the template generation system and we made some last minute tweeks at the rehersal which were causing some occasional runtime errors. Running of the software over again would usually produce the desired result. The system generated two texts for the performance, one a more abstract piece, the second a set of rhyming couplets. During testing and rehersal, the abstract piece always seemed much stronger than the rhyming couplets… but at the performance, the abstract piece came out kind of clunky, a bit too long, but the rhyming couplets were just right, humorous and strangley abstract and contextually relevant at the same time…. Unfortunately, after the performance, the texts were lost in the digital ether.

This GTR performance took place in February 2005 at the playwright Tom Cone's house. It was a for for the Songroom event which featured interdisciplanary collaborative performances between various artists and technologists.

A recording of the rehearsal session can be found here.

This track features Andrew Klobucar working a version of GTR's lyrical text generation software the output of which was immediately performed by the singer Vivian Houle, whose voice was simultaneously transformed by Stefan Smulovitz 's real time granular synthesis software KENAXIS.

This GTR performance took place in February 2005 at the playwright Tom Cone's house. It was a rehearsal for the Songroom event which featured interdisciplanary collaborative performances between various artists and technologists.

This track features Andrew Klobucar working a version of GTR's lyrical text generation software the output of which was immediately performed by the singer Vivian Houle, whose voice was simultaneously transformed by Stefan Smulovitz 's real time granular synthesis software KENAXIS .

Last year i worked on a templating language and interpretive engine to generate text. The system functioned very similar to the way the Andrew Bulhak’s Dada text generation engine worked (similar grammar etc..). The Dada engine was responsible for the well known Postmodern Essay Generator. I’ve expanded on the functionality quite a bit to tie in with some code i’ve written the last little whlie to find rhymes for certain words. The rhyming engine has knowledge of 11 types of rhyme.

Perl

Below are links to information about the language, books on learning and using Perl, links to various distributions for download and a long list of various Perl modules one can download to add functionality to their programs. Experiment and have fun !

The Dictionary Project is a poetic and theoretical investigative project aimed at the construction of software which generates new domain specific terminology using an ontologically driven text generation system. The software not only creates new words which have never before existed, but definitions for the words themselves which simulates the knowledge creation process.

• For some examples of definitions created by the system, click here to view an excerpt from a the Kootenay School of Writing's W magazine (Issue #9) .

Wow ! is making a comback in 2006.... Google recently launched their "Google Trends " site which enables the user to enter a few search terms and view their corresponding frequency distributions over time. Most frequency related data for words is usually restricted to usage counts within a particular text, or throughout a set of texts without any temporal attributes factored in.

As the name might imply, the “workbench” is essentially a digital writing tool able to perform transformative, generative and analysing functions on natural language texts.

Technically, this software project means to explore how creative writing (and language use in general) might take advantage of digital processing applications to create new and innovative forms of literary art, electronic or otherwise. The tool can best be described as a digital studio for language which allows for any number of literary and aesthetic modifications to texts, similar to the way current graphic design software like Photoshop and audio software like Sound Forge permit artists to create, modify and combine different visual and sound pieces. Through a collection of various pattern matchers, the software can detect numerous linguistic structures both syntactic and semantic. The pattern matchers create linguistic data models by generating annotations on a text. Document processors act on these annotations to perform analysis, transformations, or to generate new texts. The software functions similar to existing word processing software, but greatly extends the compositional options available which have not changed much in traditional word processing applications since their initial development in the early 1980s.