Search

In this article, we investigate the case of human-machine dialogues in the specific domain of commercial customer care. We built a corpus of conversations between users and a customer-care chatbot of an Italian Telecom Company, focusing on a sample of conversations where users contact the service asking for explanations about billing issues or overcharges. We observed that users’ requests are often vague, generic or incomprehensible. In such cases, commercial dialogue systems typically ask for clarifications or further details to fully understand users’ specific requests. However, from the corpus analysis it appeared that chatbot's clarifying requests may result in ineffective interactions, with users eventually giving up the conversation or switching to a human agent for a faster query resolution. A recovery strategy is thus needed to anticipate users’ information needs, or intentions. We address this issue resorting to GEN-DS, a dialogue system based on symbolic data-to-text generation. GEN-DS analyzes the user-company contextual relational knowledge, with the aim to generate more relevant answers to unclear questions. In this article, we describe the GEN-DS architecture along with the experiments we carried out to evaluate its output. Results from an offline human evaluation show significant improvements of GEN-DS compared to the original system. These improvements concern properties such as utility, necessity, understandability, and quickness of the information communicated in the dialogue. We believe that GEN-DS techniques may find application in all the dialogue systems that need to manage vague requests and must rely on relational knowledge.

Shared task evaluation campaigns represent a well established form of competitive evaluation, an important opportunity to propose and tackle new challenges for a specific research area and a way to foster the development of benchmarks, tools and resources. The advantages of this approach are evident in any experimental field, including the area of Natural Language Processing. An outlook on state–of–the–art language technologies for Italian can be obtained by reflecting on the results of the recently held workshop “Evaluation of NLP and Speech Tools for Italian”, EVALITA 2014. The motivations underlying individual shared tasks, the level of knowledge and development achieved within each of them, the impact on applications, society and economy at large as well as directions for future research will be discussed from this perspective.

Interaction protocols play a fundamental role in multiagent systems. In this work, after analyzing the trends that are emerging not only from research on multiagent interaction protocols but also from neighboring fields, like research on workflows and business processes, we propose a novel definition of commitment-based interaction protocols, that is characterized by the decoupling of the constitutiveand the regulativespecifications and that explicitly foresees a representation of the latter based on constraints among commitments. A clear distinction between the two representations has many advantages, mainly residing in a greater openness of multiagent systems, and an easier reuse of protocols and of action definitions. A language, named 2CL, for writing regulative specifications is also given together with a designer-oriented graphical notation.

Interaction protocols play a fundamental role in multiagent systems. In this work, after analyzing the trends that are emerging not only from research on multiagent interaction protocols but also from neighboring fields, like research on workflows and business processes, we propose a novel definition of commitment-based interaction protocols, that is characterized by the decoupling of the constitutive and the regulative specifications and that explicitly foresees a representation of the latter based on constraints among commitments. A clear distinction between the two representations has many advantages, mainly residing in a greater openness of multiagent systems, and an easier reuse of protocols and of action definitions. A language, named 2CL, for writing regulative specifications is also given together with a designer-oriented graphical notation.

The greater and greater availability of services over the web motivates the growing interest in techniques that facilitate their re-use. A web service specification can be quite complex, including various operations and message exchange patterns. In this work, we propose a rule-based declarative representation of services, and in particular of WSDL operations, that enables the application of techniques for reasoning about actions and change, that are typical of agent systems. The representation allows reasoning on choreography roles and on possible role players, to the aim of selecting services which match in a flexible way with the specification. Flexible matches are an important tool that allows web service re-use but the proposals in the literature do not guarantee the preservation of those goals, that can be proved over the role specification. We show how to enrich various well-known matches so as to produce substitutions that preserve goals and that do not require service rollback. We also discuss the problem of the joint achievement of the individual goals of a group of choreography role players.

Affective computing is receiving increasing attention in many sectors, ranging from advertisement to politics. This work, set in a Social Semantic Web framework, presents ArsEmotica, an application software for associating the predominant emotions to artistic resources of a social tagging platform. Our aim is to extract a rich emotional semantics (i.e. not limited to a positive or a negative reception) of tagged resources through an ontology driven approach. This is done by exploiting and combining available computational and sentiment lexicons with an ontology of emotional categories. The information sources we rely upon are the tags by which users annotated resources, that are available through the ArsMeteo platform, and the ontology OntoEmotion, that was enriched by means of our tool with over four hundred Italian emotional words referring to the about eighty-five emotional concepts of the ontology. Tags directly referring to ontological concepts are identified, while potentially affective tags can be annotated by using the ontology, thanks to the spontaneous intervention of the users, in a pure Web 2.0 approach. Finally, the tagged artworks are related with the emerging predominant emotions. A user study involving the ArsMeteo community was conducted in order to evaluate the ArsEmotica outcome, for what concerns the emotions automatically associated by the system to the artworks.

The specification of interaction and of the related forms of reasoning is crucial in the research area of multi-agent systems and in many application areas. This article summarizes the activities and the achievements obtained by the authors in the last years. Two are the main research lines, respectively leading to the proposal of a mentalistic approach to the specification of agent interaction policies, based on the class of grammar logics, and the proposal of a constraint-based representation of regulative and declarative patterns of interaction inside commitment-based protocols.

A typical problem of research in the area of service oriented systems is the composition of a set of services for executing a complex task. In this paper, we face an instance of this problem in which a set of parties (be their peers, agents or systems) have to interact according to a given choreography. In particular, we mean to exploit the role definitions contained in the choreography for realising interaction policies that can be executed by the involved parties. In this case, it is necessary that the choreography captures not only the interactive behaviour of the system as a whole but that the role definitions contain also a set of requirements of capabilities that the parties should exhibit, where by the term 'capability' we mean the skill of doing something or of making some condition become true. Such capabilities have the two-fold aim of connecting the interactive behaviour to be shown by the role player to its internal state and of making the policy executable.

In this paper we describe a language for reasoning about actions that can be used for modelling and for programming rational agents. We propose a modal approach for reasoning about dynamic domains in a logic programming setting. Agent behavior is specified by means of complex actionswhich are defined using modal inclusion axioms. The language is able to handle knowledge producing actions as well as actions which remove information. The problem of reasoning about complex actions with incomplete knowledge is tackled and the temporal projection and planning problems is addressed; more specifically, a goal directed proof procedureis defined, which allows agents to reason about complex actions and to generate conditional plans. We give a non-monotonicsolution for the frame problem by making use of persistency assumptions in the context of an abductive characterization. The language has been used for implementing an adaptive web-based system.