Sara Pérez-Soler

Sara Pérez-Soler

Auto-generated profile, based on publicly available information

Sara Pérez-Soler

Universidad Autónoma de Madrid, Madrid, Spain

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 February 2021 in IEEE Software
Verified
Journal Article
Closed access
SPSara Perez-Soler
Sara Perez-Soler
SJSandra Juarez-Puerta
Sandra Juarez-Puerta
EGEsther Guerra
Esther Guerra
JLJuan de Lara
Juan de Lara
Chatbots are programs that supply services to users via conversation in natural language, acting as virtual assistants within social networks or web applications. Here, we review the most representative chatbot development tools with a focus on technical and managerial aspects.

11 July 2018 in IEEE Software
Verified
Journal Article
Closed access
SPSara Perez-Soler
Sara Perez-Soler
EGEsther Guerra
Esther Guerra
JLJuan de Lara
Juan de Lara
Modelling is used in early phases of software and system development to discuss and explore problems, understand domains, evaluate alternatives and comprehend their implications. In this setting, modelling is inherently collaborative as it involves stakeholders with different backgrounds and expertise, who need to cooperate to build solutions based on consensus. However, modelling tools typically provide unwieldy diagrammatic editors that hamper the active involvement of domain experts and lack mechanisms to ease decision-making. To tackle these issues, we embed modelling within social networks, so that the interface for modelling is natural language, which a chatbot interprets to derive an appropriate domain model. Social networks have intuitive built-in discussion mechanisms, while the use of natural language lowers the entry barrier to modelling for domain experts. Moreover, we enhance modelling with soft consensus decision-making that facilitates the choice among modelling alternatives. This proposal is supported by our tool Socio, which works on social networks like Telegram.

29 October 2020
Verified
Book Chapter
Closed access
PDF file
SPSara Pérez-Soler
Sara Pérez-Soler
EGEsther Guerra
Esther Guerra
JLJuan de Lara
Juan de Lara

8 July 2024
Verified
Conference Paper
Open access
JCJesús Sánchez Cuadrado
Jesús Sánchez Cuadrado
SPSara Pérez-Soler
Sara Pérez-Soler
EGEsther Guerra
Esther Guerra
JLJuan De Lara
Juan De Lara
Task-oriented chatbots are increasingly used to access all sorts of services – like booking a flight, or setting a medical appointment – through natural language conversation. There are many technologies for implementing task-oriented chatbots, including Dialogflow, Watson, and Rasa. They rely on an explicit definition of the user intents, conversation flows, and chatbot outputs, which is costly to specify, and sometimes results in suboptimal user experiences and artificial conversations with limited diversity of chatbot responses. Recently, the advances in generative artificial intelligence fostered by Large Language Models (LLMs) have enabled a new range of open-domain chatbots, like ChatGPT, able to converse fluently on any topic. However, they are general-purpose, and therefore not directly usable to solve specialised tasks reliably. In this paper, we study the power of LLMs to build task-oriented chatbots, resulting in lighter specifications – no intent definition required – and more natural conversations than in intent-based approaches. To this end, we propose a lightweight domain-specific language based on YAML to specify chatbots using modules of different types (e.g., menus, question-answering, data gathering). These specifications are compiled into structured LLM prompts that use the ReAct framework to inform our runtime how to interpret the user input and coordinate the tasks that the chatbot must perform. The paper presents the design and realisation of our framework, and an assessment that encodes a set of existing intent-based chatbots using our approach, showing its benefits in terms of specification size, conversation flexibility and output diversity.

1 October 2017
Verified
Conference Paper
Closed access
SPSara Perez-Soler
Sara Perez-Soler
EGEsther Guerra
Esther Guerra
JLJuan de Lara
Juan de Lara
FJFrancisco Jurado
Francisco Jurado
We are witnessing a rising role of mobile computing and social networks to perform all sorts of tasks. This way, social networks like Twitter or Telegram are used for leisure, and they frequently serve as a discussion media for work-related activities. In this paper, we propose taking advantage of social networks to enable the collaborative creation of models by groups of users. The process is assisted by modelling bots that orchestrate the collaboration and interpret the users' inputs (in natural language) to incrementally build a (meta-)model. The advantages of this modelling approach include ubiquity of use, automation, assistance, natural user interaction, traceability of design decisions, possibility to incorporate coordination protocols, and seamless integration with the user's normal daily usage of social networks. We present a prototype implementation called SOCIO, able to work over several social networks like Twitter and Telegram, and a preliminary evaluation showing promising results.

1 January 2019 in The Journal of Object Technology
Verified
Journal Article
Closed access
SPSara PérEz-Soler
Sara PérEz-Soler
MGMario GonzálEz-JiménEz
Mario GonzálEz-JiménEz
EGEsther Guerra
Esther Guerra
JLJuan de Lara
Juan de Lara