Cross-community learning incorporates data from different sources to leverage task-specific solutions in a target community. This approach is particularly interesting for low-resource or newly created online communities, where data formalizing interactions between agents (community members) are limited. In such scenarios, a normative system that intends to regulate online interactions faces the challenge of continuously learning the meaning of norm violation as communities' views evolve, either with changes in the understanding of what it means to violate a norm or with the emergence of new violation classes. To address this issue, we propose the Cross-community Adapter Learning (CAL) framework, which combines adapters and transformer-based models to learn the meaning of norm violations expressed as textual sentences. Additionally, we analyze the differences in the meaning of norm violations between communities, using Integrated Gradients (IG) to understand the inner workings of our model and calculate a global relevance score that indicates the relevance of words for violation detection. Results show that cross-community learning enhances CAL's performance while explaining the differences in the meaning of norm-violating behavior based on community members' feedback. We evaluate our proposal in a small set of interaction data from Wikipedia, in which the norm prohibits hate speech.

Software Engineering (SE) communities such as Stack Overflow have become unwelcoming, particularly through members’ use of offensive language. Research has shown that offensive language drives users away from active engagement within these platforms. This work aims to explore this issue more broadly by investigating the nature of offensive language in comments posted by users in four prominent SE platforms – GitHub, Gitter, Slack and Stack Overflow (SO). It proposes an approach to detect and classify offensive language in SE communities by adopting natural language processing and deep learning techniques. Further, a Conflict Reduction System (CRS), which identifies offence and then suggests what changes could be made to minimize offence has been proposed. Beyond showing the prevalence of offensive language in over 1 million comments from four different communities which ranges from 0.07% to 0.43%, our results show promise in successful detection and classification of such language. The CRS system has the potential to drastically reduce manual moderation efforts to detect and reduce offence in SE communities.

To promote efficient interactions in dynamic and multi-agent systems, there is much interest in techniques that allow agents to represent and reason about social norms that govern agent interactions. Much of this work assumes that norms are provided to agents, but some work has investigated how agents can identify the norms present in a society through observation and experience. However, the norm-identification techniques proposed in the literature often depend on a very specific and domain-specific representation of norms, or require that the possible norms can be enumerated in advance. This paper investigates the problem of identifying norm candidates from a normative language expressed as a probabilistic context-free grammar, using Markov Chain Monte Carlo (MCMC) search. We apply our technique to a simulated robot manipulator task and show that it allows effective identification of norms from observation.

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to the reparameterization of the latent variable in another domain. Specifically, deep representations of the source and target domains are first extracted by a unified inference model and aligned by employing gradient reversal. Second, the learned deep representations are cross-modulated to the latent encoding of the alternate domain. The consistency between the reconstruction from the modulated latent encoding and the generation using deep representation samples is then enforced in order to produce inter-class alignment in the latent space. We apply the proposed model to a number of transfer learning tasks including unsupervised domain adaptation and image-to-image translation. Experimental results show that our model gives competitive performance.

Autonomous agents are increasingly required to be able to make moral decisions. In these situations, the agent should be able to reason about the ethical bases of the decision and explain its decision in terms of the moral values involved. This is of special importance when the agent is interacting with a user and should understand the value priorities of the user in order to provide adequate support. This paper presents a model of agent behavior that takes into account user preferences and moral values.

When entering a system, an agent should be aware of the obligations and prohibitions (collectively norms) that affect it. Existing solutions to this norm identification problem make use of observations of either norm compliant, or norm violating, behaviour. Thus, they assume an extreme situation where norms are typically violated, or complied with. In this paper we propose a Bayesian approach to norm identification which operates by learning from both norm compliant and norm violating behaviour. We evaluate our approach's effectiveness empirically and compare its accuracy to existing approaches. By utilising both types of behaviour, we not only overcome a major limitation of such approaches, but also obtain improved performance over the state of the art, allowing norms to be learned with fewer observations.

Before deploying a software system we need to assure ourselves (and stakeholders) that the system will behave correctly. This assurance is usually done by testing the system. However, it is intuitively obvious that adaptive systems, including agent-based systems, can exhibit complex behaviour, and are thus harder to test. In this paper we examine this "obvious intuition" in the case of Belief-Desire-Intention (BDI) agents. We analyse the size of the behaviour space of BDI agents and show that although the intuition is correct, the factors that influence the size are not what we expected them to be. Specifically, we found that the introduction of failure handling had a much larger effect on the size of the behaviour space than we expected. We also discuss the implications of these findings on the testability of BDI agents.

Abstract Scientific literature is an important medium for disseminating scientific knowledge. However, in recent times, a dramatic increase in research output has resulted in challenges for the research community. An increasing need is felt for tools that exploit the full content of an article and provide insightful services with value beyond quantitative measures such as impact factors and citation counts. However, the intricacies of language and thought, and the unstructured format of research articles present challenges in providing such services. The identification of sentence contexts that encode the role of specific sentences in advancing an article's scientific argument can facilitate in developing intelligent tools for the research community. This paper describes our research work in this direction. First, we investigate the possibility of identifying contexts associated with sentences and propose a scheme of thirteen context type definitions for sentences, based on the generic rhetorical pattern found in scientific articles. We then present the results of our experiments using sequential classifiers – conditional random fields – for achieving automatic context identification. We also describe our Semantic Web application developed for providing citation context based information services for the research community. Finally, we present a comparison and analysis of our results with similar studies and explain the distinct features of our application.

One approach to moderating the expected behaviour of agents in open societies is the use of explicit languages for defining norms, conditional commitments and/or social expectations, together with infrastructure supporting conformance checking. This article presents a logical account of the fulfilment and violation of social expectations modelled as conditional rules over a hybrid linear propositional temporal logic. Our semantics captures the intuition that the fulfilment or violation of an expectation must be determined without recourse to information from later states.We define a means of updating expectations from one state to the next based on formula progression, and show how conformance checking was implemented by combining the MCFULLmodel checking algorithm of Franceschet and de Rijke and the semantics for LTL over truncated paths proposed by Eisner et al. We present algorithms for both traditional offline model checking, where the complete model is available at once, and online model checking, where states are added to the model sequentially at runtime.

In this paper we describe how our previously proposed role model agent mechanism for norm emergence can be applied to artificial agent societies with network topologies that are changing dynamically. Dynamically changing network topologies account fo

In tackling data mining and pattern recognition tasks, finding a compact but effective set of features has often been found to be a crucial step in the overall problem-solving process. In this paper, we present an empirical study on feature analysis for recognition of classical instrument, using machine learning techniques to select and evaluate features extracted from a number of different feature schemes. It is revealed that there is significant redundancy between and within feature schemes commonly used in practice. Our results suggest that further feature analysis research is necessary in order to optimize feature selection and achieve better results for the instrument recognition problem.

Rapid changes in the business environment call for more flexible and adaptive workflow systems. Researchers have proposed that workflow management systems (WfMSs) comprising multiple agents can provide these capabilities. We have developed a multi-agent based workflow system, JBees, which supports distributed process models and the adaptability of executing processes. Modern workflow systems should also have the flexibility to integrate available Web services as they are updated. In this paper, we discuss how our agent-based architecture can be used to bind and access Web services in the context of executing a workflow process model. We use an example from the diamond processing industry to show how our agent architecture can be used to integrate Web services with WfMSs.

The paper proposes a novel view based consistency model for distributed shared memory. A view is a set of ordinary, data objects that a processor has the right to access in a data-race-free program. The view based consistency model only requires that the data objects of a view are updated before a processor accesses them. Compared with other memory consistency models, the view based consistency model can achieve data selection without user annotation and can reduce much false-sharing effect. This model has been implemented based on TreadMarks. Performance results have shown that for all our applications, the view based consistency model outperforms the lazy release consistency model.

The use of modelling abstractions to map from items in the real-world to objects in the computational domain is useful both for the effective implementation of abstract problem solutions and for the management of software complexity. This paper discusses the new approach of agent-oriented software engineering (AOSE), which uses the notion of an autonomous agent as its fundamental modelling abstraction. For the AOSE approach to be fully exploited, software engineers must be able to gain leverage from an agent software architecture and framework, and there are several such frameworks now publicly available. At the present time however there is little information concerning the options that are available and what needs to be considered when choosing or developing an agent framework. We consider three different agent software architectures that are (or will be) publicly available and evaluate some of the design and architectural differences and trade-offs that are associated with them and their impact on agent-oriented software development. Our discussion examines these frameworks in the context of an example in the area of distributed information systems.