A normative framework for agent-based systems

One of the key issues in the computational representation of open societies relates to the introduction of norms that help to cope with the heterogeneity, the autonomy and the diversity of interests among their members. Research regarding this issue presents two omissions. One is the lack of a canonical model of norms that facilitates their implementation, and that allows us to describe the processes of reasoning about norms. The other refers to considering, in the model of normative multi-agent systems, the perspective of individual agents and what they might need to effectively reason about the society in which they participate. Both are the concerns of this paper, and the main objective is to present a formal normative framework for agent-based systems.

Natural deduction system in paraconsistent setting: proof search for PCont

This paper continues a systematic approach to build natural deduction calculi and corresponding proof procedures for non-classical logics. Our attention is now paid to the framework of paraconsistent logics. These logics are used, in particular, for reasoning about systems where paradoxes do not lead to the `deductive explosion', i.e., where formulae of the type `A follows from false', for any A, are not valid. We formulate the natural deduction system for the logic PCont, explain its main concepts, define a proof searching technique and illustrate it by examples. The presentation is accompanied by demonstrating the correctness of these developments.

Are Deep Learning Approaches Suitable for Natural Language Processing?

In recent years, Deep Learning (DL) techniques have gained much at-tention from Artificial Intelligence (AI) and Natural Language Processing (NLP) research communities because these approaches can often learn features from data without the need for human design or engineering interventions. In addition, DL approaches have achieved some remarkable results. In this paper, we have surveyed major recent contributions that use DL techniques for NLP tasks. All these reviewed topics have been limited to show contributions to text understand-ing, such as sentence modelling, sentiment classification, semantic role labelling, question answering, etc. We provide an overview of deep learning architectures based on Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Recursive Neural Networks (RNNs).