A Master-Apprentice Approach to Automatic Creation of Culturally Satirical Movie Titles

Proceedings of the 14th International Conference on the Foundations of Digital Games

Alnajjar

2019

Self Cite

Role playing games rely typically on hand-written dialog that has no flexibility in adapting to the game state such as the level of the player. This is an even bigger problem for open world RPGs that make it possible to complete the game quests and objectives virtually in any given order. We present a computationally creative method for adapting Fallout 4 dialog to the changes in the game state using word embeddings for semantics and a BRNN for sequence-to-sequence paraphrasing of syntax.

Section: Discussionmentioning

confidence: 99%

“…The player can move freely in the world and complete quests in almost any given order. Fallout 4 1 , the focus of our paper, is an example of a game of this nature. However open the game world, what makes it less immersing is the fact that all the dialog in the game has been scripted and voice-acted beforehand.…”

Section: Introductionmentioning

confidence: 99%

Creative contextual dialog adaptation in an open world RPG

Proceedings of the 14th International Conference on the Foundations of Digital Games

Alnajjar

2019

Self Cite

“…5. On Evaluation of Computationally Creative Systems for more) 1 https://web.archive.org/web/20170402185912/http://prosecco-network.eu/blog/scoffing-mere-generati on If a definition for creativity is provided, the problem becomes easier to model, and it becomes easier to critically assess the degree to which a system is creative (see Alnajjar & Hämäläinen, 2018). This thinking is at the core of my thesis and it is reflected by papers II and III.…”

Section: T Heories Of C Omputational C Reativitymentioning

confidence: 99%

Generating Creative Language - Theories, Practice and Evaluation

2020

Preprint

Self Cite

This thesis presents approaches to computationally creative natural language generation focusing on theoretical foundations, practical solutions and evaluation. I defend that a theoretical definition is crucial for computational creativity and that the practical solution must closely follow the theoretical definition. Finally, evaluation must be based on the underlying theory and what was actually modelled in the practical solution. A theoretical void in the existing theoretical work on computational creativity is identified. The existing theories do not explicitly take into account the communicative nature of natural language. Therefore, a new theoretical framework is elaborated that identifies how computational creativity can take place in a setting that has a clear communicative goal. This introduces a communicative-creative trade off that sets limits to creativity in such a communicative context. My framework divides creativity in three categories: message creativity, contextual creativity and communicative creativity. Any computationally creative NLG approach not taking communicativity into account is called mere surface generation.I propose a novel master-apprentice approach for creative language generation. The approach consists of a genetic algorithm, the fitness functions of which correspond to different parameters defined as important for the creative task in question from a theoretical perspective. The output of the genetic algorithm together with possible human authored data are used to train the apprentice, which is a sequence-to-sequence neural network model. The role of the apprentice in the system is to approximate creative autonomy.Evaluation is approached from three different perspectives in this work: ad-hoc and abstract, theory-based and abstract, and theory-based and concrete. The first perspective is the most common one in the current literature and its shortcomings are demonstrated and discussed. This starts a gradual shift towards more meaningful evaluation by first using proper theories to define the task being modelled and finally reducing the room for subjective interpretation by suggesting the use of concrete evaluation questions.

“…[1,8]). Furthermore, promising results have been obtained in research using a genetic algorithm for generating parallel data for an NMT model [2,10].…”

Section: Inputmentioning

confidence: 99%

A Template Based Approach for Training NMT for Low-Resource Uralic Languages - A Pilot with Finnish

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence

Alnajjar

2019

Self Cite

In this paper, we present a novel way of building parallel data by filling abstract morphosyntactic structures for endangered lowresource languages that exhibit a rich productive morphology. We use Finnish to pilot our approach by limiting the resources we feed into the machine translation model to the level of the resources available for Erzya. We also present a way of automatically mapping abstract morphosyntactic structures of two languages to produce a parallelized set of templates.