Towards a Black Box Approximation to Human Processing of Narratives Based on Heuristics over Surface Form
نویسندگان
چکیده
Computational Narrative has provided several examples of how to process narrations using semantical approaches. While many useful concepts for computational management of stories have been unveiled, a common barrier has hindered their development: semantic knowledge is still too complex to handle. In this paper, a focus shift based on narrative structure is proposed. Instead of digging deeper into the possibilities of semantic processing, analysing structural properties of stories and keeping the semantic load to a minimum can allow for a more efficient use of available narrative corpora, even without mimicking human behaviour.
منابع مشابه
Explaining the Level of Human Thought in the Parallel Civilizations Based on Formal Structure and Visual Imagination Formed in Mythical Narratives
Myth, like any other form of narrative, has an undeniable role in visual imagination based on the foundations of mythical thought. Ernst Cassirer, by recovering the fundamental principles of mythical thought, brings against them to the foundations of contemporary rational thought and defines the fundamental features of mythical thought as compared to modern rational thought. He also believes t...
متن کاملA New Hybrid Meta-Heuristics Approach to Solve the Parallel Machine Scheduling Problem Considering Human Resiliency Engineering
This paper proposes a mixed integer programming model to solve a non-identical parallel machine (NIPM) scheduling with sequence-dependent set-up times and human resiliency engineering. The presented mathematical model is formulated to consider human factors including Learning, Teamwork and Awareness. Moreover, processing time of jobs are assumed to be non-deterministic and dependent to their st...
متن کاملLinear Programming for Heuristics in Optimal Planning
Many recent planning heuristics are based on LP optimization. However, planning experts mostly use LP solvers as a black box and it is often not obvious to them which LP techniques would be most suitable for their specific applications. To foster the communication between the planning and the optimization community, this paper gives an easily accessible overview over these recent LP-based heuri...
متن کاملUniversal Approximation with Non-sigmoid Hidden Layer Activation Functions by Using Artificial Neural Network Modeling
Neural networks are modeled on the way the human brain. They are capable of learning and can automatically recognize by skillfully training and design complex relationships and hidden dependencies based on historical example patterns and use this information for forecasting. The main difference, and at the same time is biggest advantage of the model of neural networks over statistical technique...
متن کاملDistributed Black-Box Software Testing Using Negative Selection
In the software development process, testing is one of the most human intensive steps. Many researchers try to automate test case generation to reduce the manual labor of this step. Negative selection is a famous algorithm in the field of Artificial Immune System (AIS) and many different applications has been developed using its idea. In this paper we have designed a new algorithm based on nega...
متن کامل