computational linguistics

Pedro Barbosa recalls in this interview his memories of the first studies and works of electronic literature back in the 1970s when he was a student at the University of Porto. Starting from considerations about his collaborative works he makes a comparison between printed literature tradition and the age of new media focusing on the paradigmatic change of this very transitional period with live in and the differences of the creative work. Furthermore he makes an interesting statement on regard of the aesthetics of new media by comparing works of electronic literature with the oral tradition. In the end he mentions some of the milestones of electronic literature that he considers important.

This book is addressed to computer scientists interested in the creation of new tools for digital humanities and philologists who want to introduce ITC in teaching literature in the classroom. This volume collects a group of studies related to interaction between humanities and new technologies. It has been carried out by professors and researchers from Complutense University, Universidad Federal de Santa Catarina (Brasil) and Grupo Ciberimaginario-ICONO14, which deal with creation of repositories of learning objects, the construction of virtual museums and collaborative annotation from digital documents, specially literary ones.

A general method for the generation of natural language narrative is described. It allows the expression, or narrative discourse, to vary independently of the underlying events and existents that are the narrative’s content. Specifically, this variation is accomplished in an interactive fiction (IF) system which replies to typed input by narrating what has happened in a simulated world. IF works have existed for about 30 years as forms of text-based computer simulation, instances of dialog systems, and examples of literary art. Theorists of narrative have carefully distinguished between the level of underlying content (corresponding to the simulated world in interactive fiction) and that of expression (corresponding to the textual exchange between computer arnd user) since the mid-1960s, when the field of narratology began to develop, but IF systems have not yet made use of this distinction. The current project contributes new techniques for automatic narration by building on work done in computational linguistics, specifically natural language generation, and in narratology. First, types of narrative variation that are possible in IF are identified and formalized in a way that is suitable for a natural language generation system. An architecture for an IF system is then described and implemented; the result allows multiple works of interactive fiction to be realized and, using a general plan for narrating, allows them to be narrated in different ways during interaction. The system’s ability to generate text is considered in a pilot evaluation. Plans for future work are also discussed. They include publicly released systems for IF development and narratology education, adding a planning capability that uses actors’ individual perspectives, and adapting automatic narration to different sorts of interactive systems.

(Source: Author's abstract)

Various forms of computational linguistics and various forms of electronic literature have been aiming to create an algorithm capable of imitating natural human language. The highest Turing test approval for a chatterbot would be impossibility to tell this program from a real person. And therefore, poetry and story generators are often criticized as artificial and in need of further «humanization». In the paper I am going to prove the virtue of producing not human-like computer generated poetry and illustrate my points with the example of Machine Libertine project works.

The perception of something as machine-like is rather relative and depends on the degree to which the medium is explored (early photography was seen to mechanic to be art). Meanwhile the flaw is in this contrast between the ideas of «mechanicity» and «artness», because «natural» has even less rights to be called art. Mechanized writing as such, according to William Winder, is an explicit device of creation. It has been studied by various aleatoric practices and combinatoric experiments of OULIPO; and even traditional poetry is based on unnatural constrains of rhythm and rhyme that separate profane language from poetic.

In itself the two-decade history of the existence of net art and computer generated art aethetics can be seen as legitimization of the practice. Isak Asimov introduces the Rules of Robotics, and one of them suggests: «A robot must establish its identity as a robot». Applied to robotic poetry, this statement proves the necessity and virtue of the manifestation of its mechanic nature. Machine Libertines by the implementation of synthesized MacOs voice and machine translation methods stress the instability of the transformational nature of the video poetry and media art in general.

Machine Libertine is a newly created media poetry group. The main principles of the group are
formulated in the Machine Poetry Manifesto and agree with Eugenio Tisselli's «manifesto about machine poetry. manifesto for the destruction of poets» in pointing out the idea of liberation of the machines from the routine tasks and increasing the intensity of their use for creative and educational practices. The first video poetry piece, created by Machine Libertines, «Snow Queen» is a combination of masculine poetry of hatred («Poison Tree» by William Blake) that is contrasted to female MacOS voice and cubistic video imagery of Souzfilm animation «Snow Queen». Reading in Vicky's voice alters the orignal text's message, adding hopless and clean cold of the icy mechanisity. We are exploring how the text can be transformed by mechanized reading and visualizing it and what are the possible limits of this transmedia play of interpretation.

(Source: Author's abstract, 2012 ELO Conference site)

People draw on many diverse sources of real-world knowledge in order to make up stories, including the following: knowledge of the physical world; rules of social behavior and relationships; techniques for solving everyday problems such as transportation, acquisition of objects, and acquisition of information; knowledge about physical needs such as hunger and thirst; knowledge about stories their organization and contents; knowledge about planning behavior and the relationships between kinds of goals; and knowledge about expressing a story in a natural language. This thesis describes a computer program which uses all information to write stories. The areas of knowledge, called problem domains, are defined by a set of representational primitives, a set of problems expressed in terms of those primitives, and a set of procedures for solving those problems. These may vary from one domain to the next. All this specialized knowledge must be integrated in order to accomplish a task such as storytelling. The program, called TALE-SPIN, produces stories in English, interacting with the user, who specifies characters, personality characteristics, and relationships between characters. Operating in a different mode, the program can make those decisions in order to produce Aesop-like fables.

(Source: Author's abstract)