Dimitar Kazakov | University of York (original) (raw)

Uploads

Papers by Dimitar Kazakov

Cognitive Computation, May 10, 2012

Abstract This work discusses the challenge of developing self-cognisant artificial intelligence s... more Abstract This work discusses the challenge of developing self-cognisant artificial intelligence systems, looking at the possible benefits and the main issues in this quest. It is argued that the degree of complexity, variation, and specialisation of technological artefacts used nowadays, along with their sheer number, represent an issue that can and should be addressed through an important step towards greater autonomy, that is, the integration of learning, which will allow the artefact to observe its own functionality and build a model of ...

International Journal on Cybernetics & Informatics

Consideration of multiple viewpoints on a contentious issue is critical for avoiding bias and ass... more Consideration of multiple viewpoints on a contentious issue is critical for avoiding bias and assisting in the formulation of rational decisions. We observe that the current model imposes a constraint on diversity. This is because the conventional attention mechanism is biased toward a single semantic aspect of the claim, whereas the claim may contain multiple semantic aspects. Additionally, disregarding common-sense knowledge may result in generating perspectives that violate known facts about the world. The proposed approach is divided into two stages: the first stage considers multiple semantic aspects, which results in more diverse generated perspectives; the second stage improves the quality of generated perspectives by incorporating common-sense knowledge. We train the model on each stage using reinforcement learning and automated metric scores. The experimental results demonstrate the effectiveness of our proposed model in generating a broader range of perspectives on a conte...

Lecture Notes in Networks and Systems, 2021

Fact-checking is a task to capture the relation between a claim and evidence (premise) to decide ... more Fact-checking is a task to capture the relation between a claim and evidence (premise) to decide this claim’s truth. Detecting the factuality of claim, as in fake news, depending only on news knowledge, e.g., evidence text, is generally inadequate since fake news is intentionally written to mislead readers. Most of the previous models on this task rely on claim and evidence argument as input for their model, where sometimes the systems fail to detect the relation, particularly for ambiguate information. This study aims to improve fact-checking task by incorporating warrant as a bridge between the claim and the evidence, illustrating why this evidence supports this claim, i.e., If the warrant links between the claim and the evidence then the relation is supporting, if not it is either irrelevant or attacking, so warrants are applicable only for supporting the claim. To solve the problem of gap semantic between claim evidence pair, A model that can detect the relation based on existing extracted warrants from structured data is developed. For warrant selection, knowledge-based prediction and style-based prediction models are merged to capture more helpful information to infer which warrant represents the best bridges between claim and evidence. Picking a reasonable warrant can help alleviate the evidence ambiguity problem if the proper relation cannot be detected. Experimental results show that incorporating the best warrant to fact-checking model improves the performance of fact-checking.

2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), 2021

Proceedings of the Genetic and Evolutionary Computation Conference Companion

Hybridisation of algorithms in evolutionary computation (EC) has been used by researchers to over... more Hybridisation of algorithms in evolutionary computation (EC) has been used by researchers to overcome drawbacks of population-based algorithms. The introduced algorithm called mutated Artificial Bee Colony algorithm, is a novel variant of standard Artificial Bee Colony algorithm (ABC) which successfully moves out of local optima. First, new parameters are found and tuned in ABC algorithm. Second, the mutation operator is employed which is responsible for bringing diversity into solution. Third, to avoid tuning 'limit' parameter and prevent abandoning good solutions, it is replaced by average fitness comparison of worst employed bee. Thus, proposed algorithm gives the global solution thus improving the exploration capability of ABC. The proposed algorithm is tested on four classes of problems. The results are compared with six other population-based algorithms, namely Genetic Algorithm (GA), Particle Swarm Optimsation (PSO), Differential Evolution (DE), standard Artificial Bee Colony algorithm (ABC) and its two variants- quick Artificial Bee Colony algorithm (qABC) and adaptive Artificial Bee Colony algorithm (aABC). Overall results show that mutated ABC is at par with aABC and better than above-mentioned algorithms. The novel algorithm is best suited to 3 of the 4 classes of functions under consideration. Functions belonging to UN class have shown near optimal solution.

HAL (Le Centre pour la Communication Scientifique Directe), Jun 9, 2021

ArXiv, 2020

We conduct an exhaustive survey of adaptive selection of operators (AOS) in Evolutionary Algorith... more We conduct an exhaustive survey of adaptive selection of operators (AOS) in Evolutionary Algorithms (EAs). We simplified the AOS structure by adding more components to the framework to built upon the existing categorisation of AOS methods. In addition to simplifying, we looked at the commonality among AOS methods from literature to generalise them. Each component is presented with a number of alternative choices, each represented with a formula. We make three sets of comparisons. First, the methods from literature are tested on the BBOB test bed with their default hyper parameters. Second, the hyper parameters of these methods are tuned using an offline configurator known as IRACE. Third, for a given set of problems, we use IRACE to select the best combination of components and tune their hyper parameters.

Demographic events often leave traces in languages and genes: this prompted Darwin’s prediction t... more Demographic events often leave traces in languages and genes: this prompted Darwin’s prediction that the evolutionary tree of human populations would provide the best possible phylogeny of language relationships. We tested Darwin’s expectation through long-distance genome-language comparisons across Eurasia, relying on independently assessed quantitative tools on both sides. To do so, we had to resort to a linguistic method able to compare across different families, based on abstract syntactic characters, which proved more apt for long-term historical reconstruction than phonemic ones.

Proceedings of the International Conference on Agents and Artificial Intelligence, 2009

2007 4th IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2007

Abstract Clustering multiple-instances in a multi-relational environment requires data transforma... more Abstract Clustering multiple-instances in a multi-relational environment requires data transformations (eg data aggregation) from datasets stored in multiple tables into a single table. Unfortunately, most relational databases are limited to a few basic methods of aggregation (eg max, min, sum, count, ave) to aggregate continuous and categorical values. Therefore, data transformation is limited only to aggregation of continuous and categorical values. In this paper, to get the best number of clusters, we propose a genetic semi- ...

2015 IEEE Symposium Series on Computational Intelligence, 2015

Lecture Notes in Computer Science, 2001

Lecture Notes in Computer Science, 2005

This paper presents a multi-agent system which has been developed in order to test our theories o... more This paper presents a multi-agent system which has been developed in order to test our theories of language evolution. We propose that language evolution is an emergent behaviour, which is influenced by both genetic and social factors and show that a multi-agent approach is thus most suited to practical study of the salient issues. We present the hypothesis that the original function of language in humans was to share navigational information, and show experimental support for this hypothesis through results comparing ...

Lecture Notes in Computer Science, 2003

Lecture Notes in Computer Science, 2010