Regression test prioritization leveraging source code similarity with tree kernels

F Altiero, A Corazza, S Di Martino… - Journal of Software …, 2024 - Wiley Online Library
Regression test prioritization (RTP) is an active research field, aiming at re‐ordering the
tests in a test suite to maximize the rate at which faults are detected. A number of RTP …

Auditing deep learning processes through kernel-based explanatory models

D Croce, D Rossini, R Basili - Proceedings of the 2019 …, 2019 - aclanthology.org
While NLP systems become more pervasive, their accountability gains value as a focal point
of effort. Epistemological opaqueness of nonlinear learning methods, such as deep learning …

Land use classification with point of interests and structural patterns

G Barlacchi, B Lepri, A Moschitti - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In this paper, we present a framework for performing automatic analysis of Land Use Zones
based on Location-Based Social Networks (LBSNs). We model city areas using a …

Shallow and deep syntactic/semantic structures for passage reranking in question-answering systems

K Tymoshenko, A Moschitti - ACM Transactions on Information Systems …, 2018 - dl.acm.org
In this article, we extensively study the use of syntactic and semantic structures obtained with
shallow and full syntactic parsers for answer passage reranking. We propose several …

Explaining non-linear classifier decisions within kernel-based deep architectures

D Croce, D Rossini, R Basili - Proceedings of the 2018 EMNLP …, 2018 - aclanthology.org
Nonlinear methods such as deep neural networks achieve state-of-the-art performances in
several semantic NLP tasks. However epistemologically transparent decisions are not …

HeAL9000: An intelligent rehabilitation robot

L Cristofori, CD Hromei, FS Di Luzio… - CEUR Workshop …, 2021 - iris.unicampus.it
AI applications to health related processes include the adoption of robotic platforms for
rehabilitation, aiming at the delivery of highly intensive, repeatable and accurate motion …

[КНИГА][B] Concepts and Design Thinking Innovation Addressing the Global Financial Needs: The INFINTECH Way Foundations Part I

M Serrano, B Khorsand, J Soldatos - 2023 - library.oapen.org
In this first part of the INFINITECH book series, which is a series of three books, the
principles of the modern economy that make the modern financial sector and FinTech the …

Adversarial training for few-shot text classification

D Croce, G Castellucci, R Basili - Intelligenza Artificiale, 2021 - journals.sagepub.com
In recent years, Deep Learning methods have become very popular in classification tasks for
Natural Language Processing (NLP); this is mainly due to their ability to reach high …

Automatic recognition of narrative drama units: A structured learning approach

D Croce, R Basili, V Lombardo, E Ceccaldi - Text2Story 2019 Second …, 2019 - iris.unito.it
Drama is a story told through the live actions of characters; dramatic writing is characterized
by aspects that are central to identify, interpret, and relate the different elements of a story …

U-DepPLLaMA: Universal Dependency Parsing via Auto-regressive Large Language Models

CD Hromei, D Croce, R Basili - IJCoL. Italian Journal of …, 2024 - journals.openedition.org
This paper investigates the rapidly advancing domain of Large Language Models (LLMs)
and their growing potential in various fields. A central focus is the exploration of LLMs, eg …