Author name cluster

Valerio Basile

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2023 Conference Paper

Toward a Perspectivist Turn in Ground Truthing for Predictive Computing

Federico Cabitza
Andrea Campagner
Valerio Basile

Most current Artificial Intelligence applications are based on supervised Machine Learning (ML), which ultimately grounds on data annotated by small teams of experts or large ensemble of volunteers. The annotation process is often performed in terms of a majority vote, however this has been proved to be often problematic by recent evaluation studies. In this article, we describe and advocate for a different paradigm, which we call perspectivism: this counters the removal of disagreement and, consequently, the assumption of correctness of traditionally aggregated gold-standard datasets, and proposes the adoption of methods that preserve divergence of opinions and integrate multiple perspectives in the ground truthing process of ML development. Drawing on previous works which inspired it, mainly from the crowdsourcing and multi-rater labeling settings, we survey the state-of-the-art and describe the potential of our proposal for not only the more subjective tasks (e.g. those related to human language) but also those tasks commonly understood as objective (e.g. medical decision making). We present the main benefits of adopting a perspectivist stance in ML, as well as possible disadvantages, and various ways in which such a stance can be implemented in practice. Finally, we share a set of recommendations and outline a research agenda to advance the perspectivist stance in ML.

PDF Details DOI

IJCAI Conference 2018 Conference Paper

Empirical Analysis of Foundational Distinctions in Linked Open Data

Luigi Asprino
Valerio Basile
Paolo Ciancarini
Valentina Presutti

The Web and its Semantic extension (i. e. Linked Open Data) contain open global-scale knowledge and make it available to potentially intelligent machines that want to benefit from it. Nevertheless, most of Linked Open Data lack ontological distinctions and have sparse axiomatisation. For example, distinctions such as whether an entity is inherently a class or an individual, or whether it is a physical object or not, are hardly expressed in the data, although they have been largely studied and formalised by foundational ontologies (e. g. DOLCE, SUMO). These distinctions belong to common sense too, which is relevant for many artificial intelligence tasks such as natural language understanding, scene recognition, and the like. There is a gap between foundational ontologies, that often formalise or are inspired by pre-existing philosophical theories and are developed with a top-down approach, and Linked Open Data that mostly derive from existing databases or crowd-based effort (e. g. DBpedia, Wikidata). We investigate whether machines can learn foundational distinctions over Linked Open Data entities, and if they match common sense. We want to answer questions such as “does the DBpedia entity for dog refer to a class or to an instance? ”. We report on a set of experiments based on machine learning and crowdsourcing that show promising results.

PDF Details

ICRA Conference 2017 Conference Paper

Semantic web-mining and deep vision for lifelong object discovery

Jay Young
Lars Kunze
Valerio Basile
Elena Cabrio
Nick Hawes
Barbara Caputo

Autonomous robots that are to assist humans in their daily lives must recognize and understand the meaning of objects in their environment. However, the open nature of the world means robots must be able to learn and extend their knowledge about previously unknown objects on-line. In this work we investigate the problem of unknown object hypotheses generation, and employ a semantic Web-mining framework along with deep-learning-based object detectors. This allows us to make use of both visual and semantic features in combined hypotheses generation. Experiments on data from mobile robots in real world application deployments show that this combination improves performance over the use of either method in isolation.

Details

ECAI Conference 2016 Conference Paper

Towards Lifelong Object Learning by Integrating Situated Robot Perception and Semantic Web Mining

Jay Young
Valerio Basile
Lars Kunze
Elena Cabrio
Nick Hawes

Autonomous robots that are to assist humans in their daily lives are required, among other things, to recognize and understand the meaning of task-related objects. However, given an open-ended set of tasks, the set of everyday objects that robots will encounter during their lifetime is not foreseeable. That is, robots have to learn and extend their knowledge about previously unknown objects on-the-job. Our approach automatically acquires parts of this knowledge (e. g. , the class of an object and its typical location) in form of ranked hypotheses from the Semantic Web using contextual information extracted from observations and experiences made by robots. Thus, by integrating situated robot perception and Semantic Web mining, robots can continuously extend their object knowledge beyond perceptual models which allows them to reason about task-related objects, e. g. , when searching for them, robots can infer the most likely object locations. An evaluation of the integrated system on long-term data from real office observations, demonstrates that generated hypotheses can effectively constrain the meaning of objects. Hence, we believe that the proposed system can be an essential component in a lifelong learning framework which acquires knowledge about objects from real world observations.

Details