Fabiano Dalpiaz

Francesco Dente, Fabiano Dalpiaz, Paolo Papotti

Large language models (LLMs) can be employed for automating the generation of software requirements from natural language inputs such as the transcripts of elicitation interviews. However, evaluating whether those derived requirements faithfully reflect the stakeholders' needs remains a largely manual task. We introduce Text2Stories, a task and metrics for text-to-story alignment that allow quantifying the extent to which requirements (in the form of user stories) match the actual needs expressed by the elicitation session participants. Given an interview transcript and a set of user stories, our metric quantifies (i) correctness: the proportion of stories supported by the transcript, and (ii) completeness: the proportion of transcript supported by at least one story. We segment the transcript into text chunks and instantiate the alignment as a matching problem between chunks and stories. Experiments over four datasets show that an LLM-based matcher achieves 0.86 macro-F1 on held-out annotations, while embedding models alone remain behind but enable effective blocking. Finally, we show how our metrics enable the comparison across sets of stories (e.g., human vs. generated), positioning Text2Stories as a scalable, source-faithful complement to existing user-story quality criteria.

Davide Dell'Anna, Natasha Alechina, Brian Logan et al.

Norms have been widely proposed as a way of coordinating and controlling the activities of agents in a multi-agent system (MAS). A norm specifies the behaviour an agent should follow in order to achieve the objective of the MAS. However, designing norms to achieve a particular system objective can be difficult, particularly when there is no direct link between the language in which the system objective is stated and the language in which the norms can be expressed. In this paper, we consider the problem of synthesising a norm from traces of agent behaviour, where each trace is labelled with whether the behaviour satisfies the system objective. We show that the norm synthesis problem is NP-complete.

Omar ElAssy, Rik de Vendt, Fabiano Dalpiaz et al.

The automated capturing and summarization of medical consultations has the potential to reduce the administrative burden in healthcare. Consultations are structured conversations that broadly follow a guideline with a systematic examination of predefined observations and symptoms to diagnose and treat well-defined medical conditions. A key component in automated conversation summarization is the matching of the knowledge graph of the consultation transcript with a medical domain ontology for the interpretation of the consultation conversation. Existing general medical ontologies such as SNOMED CT provide a taxonomic view on the terminology, but they do not capture the essence of the guidelines that define consultations. As part of our research on medical conversation summarization, this paper puts forward a semi-automated method for generating an ontological representation of a medical guideline. The method, which takes as input the well-known SNOMED CT nomenclature and a medical guideline, maps the guidelines to a so-called Medical Guideline Ontology (MGO), a machine-processable version of the guideline that can be used for interpreting the conversation during a consultation. We illustrate our approach by discussing the creation of an MGO of the medical condition of ear canal inflammation (Otitis Externa) given the corresponding guideline from a Dutch medical authority.

Fabiano Dalpiaz, Xavier Franch, Jennifer Horkoff

The i* modeling language was introduced to fill the gap in the spectrum of conceptual modeling languages, focusing on the intentional (why?), social (who?), and strategic (how? how else?) dimensions. i* has been applied in many areas, e.g., healthcare, security analysis, eCommerce. Although i* has seen much academic application, the diversity of extensions and variations can make it difficult for novices to learn and use it in a consistent way. This document introduces the iStar 2.0 core language, evolving the basic concepts of i* into a consistent and clear set of core concepts, upon which to build future work and to base goal-oriented teaching materials. This document was built from a set of discussions and input from various members of the i* community. It is our intention to revisit, update and expand the document after collecting examples and concrete experiences with iStar 2.0.