An Implementation, Empirical Evaluation and Proposed Improvement for Bidirectional Splitting Method for Argumentation Frameworks under Stable Semantics
Abstract argumentation frameworks are formal systems that facilitate obtaining conclusions from non-monotonic knowledge systems. Within such a system, an argumentation semantics is defined as a set of arguments with some desired qualities, for example, that the elements are not in conflict with each other. Splitting an argumentation framework can efficiently speed up the computation of argumentation semantics. With respect to stable semantics, two methods have been proposed to split an argumentation framework either in a unidirectional or bidirectional fashion. The advantage of bidirectional splitting is that it is not structure-dependent and, unlike unidirectional splitting, it can be used for frameworks consisting of a single strongly connected component. Bidirectional splitting makes use of a minimum cut. In this paper, we implement and test the performance of the bidirectional splitting method, along with two types of graph cut algorithms. Experimental data suggest that using a minimum cut will not improve the performance of computing stable semantics in most cases. Hence, instead of a minimum cut, we propose to use a balanced cut, where the framework is split into two sub-frameworks of equal size. Experimental results conducted on bidirectional splitting using the balanced cut show a significant improvement in the performance of computing semantics.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstract ArgumentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs). However, there is currently limited understanding of why SN is effective. I…
Enhanced Penalty-based Bidirectional Reinforcement Learning Algorithms
This research focuses on enhancing reinforcement learning (RL) algorithms by integrating penalty functions to guide agents in avoiding unwanted actions while optimizing rewards. The goal is to improve the learning proces…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Linear Attention for Efficient Bidirectional Sequence Modeling
Transformers with linear attention enable fast and parallel training. Moreover, they can be formulated as Recurrent Neural Networks (RNNs), for efficient linear-time inference. While extensively evaluated in causal seque…
State Space ModelsBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bid…
Citation Intent ClassificationCommon Sense ReasoningConversational Response SelectionCoreference Resolution+17BiBL: AMR Parsing and Generation with Bidirectional Bayesian Learning
Abstract Meaning Representation (AMR) offers a unified semantic representation for natural language sentences. Thus transformation between AMR and text yields two transition tasks in opposite directions, i.e., Text-to-AM…
Abstract Meaning RepresentationAMR ParsingAMR-to-Text GenerationText Generation