Towards finer-grained interaction with a Poetry Generator

2019

In this paper, the authors propose a dialectic of pattern and randomness as an interpretative lens for electronic poetry. By examining the complex interplay of recurring patterns and randomly generated elements in two electronic poems, they demonstrate how poetry and code work together and how meaning can be made from randomly generated poetic works. They showcase two of their own electronic poetry projects as case studies, the poem Wayfarer’s Song (Okkema) and the Dada Poetry Generator (Hill). Wayfarer’s Song generates a Villanelle poem from a set of randomly chosen, pre-written verses. On the level of content, the poem exemplifies the interplay of pattern and randomness by juxtaposing arbitrary arrangement with the poetic pattern of Villanelle. Reading the poem in light of pattern and randomness reveals further layers of meaning on the levels of code, interface, and hardware. The Dada Poetry Generator engages users in creating poems from “found” texts. Because each iteration of th...

2013

Linguistic creativity is a marriage of form and content in which each works together to convey our meanings with concision, resonance and wit. Though form clearly influences and shapes our content, the most deft formal trickery cannot compensate for a lack of real insight. Before computers can be truly creative with language, we must first imbue them with the ability to formulate meanings that are worthy of creative expression. This is especially true of computer-generated poetry. If readers are to recognize a poetic turn-of-phrase as more than a superficial manipulation of words, they must perceive and connect with the meanings and the intent behind the words. So it is not enough for a computer to merely generate poem-shaped texts; poems must be driven by conceits that build an affective worldview. This paper describes a conceit-driven approach to computational poetry, in which metaphors and blends are generated for a given topic and affective slant. Subtle inferences drawn from th...

Poems are particular well-crafted formulations of certain messages that satisfy constraints on their form as well on their content. From an engineering point of view, the ability to optimize the combination of form and content is a very desireable feature to be able to model. The present paper reviews a number of efforts at modelling poetry generation computationally, and it brings together insights from these efforts into a computational model that allows integration of a number of AI technologies combined together according to control structures compatible with observed human behaviour. The relation of this computational model with existing cognitive models of the writing task, and with models of computational creativity is discussed.

2004

The ultimate goal of the poetry assistant currently under development in our lab is an application to be used either as a poetry game or as a teaching tool for both poetry and grammar, including the complex relationships between sound and meaning. Until now we focused on the automatic classification of poems and the suggestion of the ending word for a verse. The classification module is based on poetic concepts that take into account structure and metrics. The prediction module uses several criteria to select the ending word: the structural constraints of the poem, the grammatical category of the words, and the statistical language models obtained from a text corpus. The first version of the system, rather than being selfcontained, is still based on the use of different heterogeneous modules. We are currently working on a second version based on a modular architecture that facilitates the reuse of the linguistic processing modules already developed within the lab.

Proceedings of the …, 2012

We describe a corpus-based poetry generation system which uses templates to construct poems according to given constraints on rhyme, meter, stress, sentiment, word frequency and word similarity. Moreover, the software constructs a mood for the day by analysing newspaper articles; uses this to determine both an article to base a poem on and a template for the poem; creates an aesthetic based on relevance to the article, lyricism, sentiment and flamboyancy; searches for an instantiation of the template which maximises the aesthetic; and provides a commentary for the whole process to add value to the creative act. We describe the processes behind this approach, present some experimental results which helped in fine tuning, and provide some illustrative poems and commentaries. We argue that this is the first poetry system which generates examples, forms concepts, invents aesthetics and frames its work, and so can be assessed favourably with respect to the FACE model for comparing creative systems.

Proceedings of AISB Symposium …, 2000

This paper presents and evaluates a novel system for computer generated poetry. Framed within contemporary theoretical trends in the evaluation of computational creativity, we investigate how evidence of generative process influences readers' opinions of computer generated textual output. In addition to a technical description of our system, we present results from a study asking respondents to evaluate short computer generated poems prefaced with different types of descriptions, in some cases objectively presenting the poem as the product of a statistical analysis of corpora and in some cases subjectively presenting the computer as a self-aware agent.

2000

In this paper we describe a flexible approach to natural language generation that employs a stochastic hillclimbing search algorithm and an integrated architecture. We then discuss the benefits of this approach over existing, informative, goal-driven generation systems. We choose the generation of poetry as our research task domain, as it is a prime example of natural language that demands the degree of flexibility provided by our approach. Finally, we report and discuss results of our preliminary implementation work.

RATE Issues, 2024

This study explores the intersection of artificial intelligence and creative expression, focusing on the emergence of AI-generated poetry. It overviews existing literature on AI and its integration into literature, emphasizing AI poetry specifically. At the heart of this study are three poems generated by the AI model ChatGPT 4. Through a critical analysis of these poems and their prompts, the study found that, to a certain extent, AI can mirror human poetic expression producing complex poems with numerous literary devices. However, AI's creativity is constrained by training material, prompts, and prompters, signaling both AI's potential and limitations in shaping contemporary poetry.

Proceedings of the …, 2009

Computer technology has become closely integrated with modern culture, which prompted us to introduce and explore the avenues of integrating aesthetics with technology. With the intention of promoting aesthetic sensibilities generated in poetry, we introduce a poetry generating system called “Poetry Mix-up", which encourages users to experience the creation of a ‘remixed’ variety of poetry by sending a simple short message (SMS). Based on the topics and the content of the input message, the system creates a new poem by mixing existing poem lines. The preliminary user study shows that Poetry Mix-up could be a new form of social and cultural communication in the digital era.