129 citations · 283 across the 26 of their papers we have counts for
32 papers
Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
Amin Beheshti, Rong N. Chang, Boualem Benatallah +7
The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and to…
ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence
Amin Beheshti, Jian Yang, Quan Z. Sheng +6
Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is traine…
On the Value of ML Models
Fabio Casati, Pierre-André Noël, Jie Yang
We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by t…
The Science of Rejection: A Research Area for Human Computation
Burcu Sayin, Jie Yang, Andrea Passerini +1
We motivate why the science of learning to reject model predictions is central to ML, and why human computation has a lead role in this effort.
Crowdsourcing Diverse Paraphrases for Training Task-oriented Bots
Jorge Ramírez, Auday Berro, Marcos Baez +2
A prominent approach to build datasets for training task-oriented bots is crowd-based paraphrasing. Current approaches, however, assume the crowd would naturally provide diverse pa…
On the state of reporting in crowdsourcing experiments and a checklist to aid current practices
Jorge Ramírez, Burcu Sayin, Marcos Baez +4
Crowdsourcing is being increasingly adopted as a platform to run studies with human subjects. Running a crowdsourcing experiment involves several choices and strategies to successf…
Active Hybrid Classification
Evgeny Krivosheev, Fabio Casati, Alessandro Bozzon
Hybrid crowd-machine classifiers can achieve superior performance by combining the cost-effectiveness of automatic classification with the accuracy of human judgment. This paper sh…
On the impact of predicate complexity in crowdsourced classification tasks
Jorge Ramírez, Marcos Baez, Fabio Casati +4
This paper explores and offers guidance on a specific and relevant problem in task design for crowdsourcing: how to formulate a complex question used to classify a set of items. In…
Chatbots as conversational healthcare services
Mlađan Jovanović, Marcos Baez, Fabio Casati
Chatbots are emerging as a promising platform for accessing and delivering healthcare services. The evidence is in the growing number of publicly available chatbots aiming at takin…
Challenges and strategies for running controlled crowdsourcing experiments
Jorge Ramírez, Marcos Baez, Fabio Casati +2
This paper reports on the challenges and lessons we learned while running controlled experiments in crowdsourcing platforms. Crowdsourcing is becoming an attractive technique to en…
Chatbot integration in few patterns
Marcos Baez, Florian Daniel, Fabio Casati +1
Chatbots are software agents that are able to interact with humans in natural language. Their intuitive interaction paradigm is expected to significantly reshape the software lands…
Siamese Graph Neural Networks for Data Integration
Evgeny Krivosheev, Mattia Atzeni, Katsiaryna Mirylenka +2
Data integration has been studied extensively for decades and approached from different angles. However, this domain still remains largely rule-driven and lacks universal automatio…
CrowdHub: Extending crowdsourcing platforms for the controlled evaluation of tasks designs
Jorge Ramírez, Simone Degiacomi, Davide Zanella +3
We present CrowdHub, a tool for running systematic evaluations of task designs on top of crowdsourcing platforms. The goal is to support the evaluation process, avoiding potential…
Understanding the Impact of Text Highlighting in Crowdsourcing Tasks
Jorge Ramírez, Marcos Baez, Fabio Casati +1
Text classification is one of the most common goals of machine learning (ML) projects, and also one of the most frequent human intelligence tasks in crowdsourcing platforms. ML has…
Combining Crowd and Machines for Multi-predicate Item Screening
Evgeny Krivosheev, Fabio Casati, Marcos Baez +1
This paper discusses how crowd and machine classifiers can be efficiently combined to screen items that satisfy a set of predicates. We show that this is a recurring problem in man…
Technologies for promoting social participation in later life
Marcos Baez, Radoslaw Nielek, Fabio Casati +1
Social participation is known to bring great benefits to the health and well-being of people as they age. From being in contact with others to engaging in group activities, keeping…
Design Challenges for Reconnecting in Later Life: A Qualitative Study
Francisco Ibarra, Grzegorz Kowalik, Marcos Baez +4
Friendships and social interactions are renown contributors to wellbeing. As such, keeping a healthy amount of relationships becomes very important as people age and the size of th…
Designing for Co-located and Virtual Social Interactions in Residential Care
Francisco Ibarra, Marcos Baez, Francesca Fiore +1
In this paper we explore the feasibility and design challenges in supporting co-located and virtual social interactions in residential care by building on the practice of reminisce…
CrowdRev: A platform for Crowd-based Screening of Literature Reviews
Jorge Ramirez, Evgeny Krivosheev, Marcos Baez +2
In this paper and demo we present a crowd and crowd+AI based system, called CrowdRev, supporting the screening phase of literature reviews and achieving the same quality as author…
Crowdsourcing for Reminiscence Chatbot Design
Svetlana Nikitina, Florian Daniel, Marcos Baez +1
In this work-in-progress paper we discuss the challenges in identifying effective and scalable crowd-based strategies for designing content, conversation logic, and meaningful metr…
Crowd-based Multi-Predicate Screening of Papers in Literature Reviews
Evgeny Krivosheev, Fabio Casati, Boualem Benatallah
Systematic literature reviews (SLRs) are one of the most common and useful form of scientific research and publication. Tens of thousands of SLRs are published each year, and this…
Crowd-Machine Collaboration for Item Screening
Evgeny Krivosheev, Bahareh Harandizadeh, Fabio Casati +1
In this paper we describe how crowd and machine classifier can be efficiently combined to screen items that satisfy a set of predicates. We show that this is a recurring problem in…
Agile development for vulnerable populations: lessons learned and recommendations
Marcos Baez, Fabio Casati
In this paper we draw attention to the challenges of managing software projects for vulnerable populations, i.e., people potentially exposed to harm or not capable of protecting th…
Programming Bots by Synthesizing Natural Language Expressions into API Invocations
Shayan Zamanirad, Boualem Benatallah, Moshe Chai Barukh +2
At present, bots are still in their preliminary stages of development. Many are relatively simple, or developed ad-hoc for a very specific use-case. For this reason, they are typic…