0000000001136564

AUTHOR

Paolo Rosso

R2D2 at GeoCLEF 2006: A Combined Approach

This paper describes the participation of a combined approach in GeoCLEF-2006. We have participated in Monolingual English Task and we present joint work of the three groups or teams belonging to the project R2D2 with a new system, combining the three individual systems of these teams. We consider that research in the area of GIR is still in its very early stages, therefore, although a voting system could improve the individual results of each system, we have to further investigate different ways to achieve a better combination of these systems.

research product

Arabic Named Entity Recognition: A Feature-Driven Study

The named entity recognition task aims at identifying and classifying named entities within an open-domain text. This task has been garnering significant attention recently as it has been shown to help improve the performance of many natural language processing applications. In this paper, we investigate the impact of using different sets of features in three discriminative machine learning frameworks, namely, support vector machines, maximum entropy and conditional random fields for the task of named entity recognition. Our language of interest is Arabic. We explore lexical, contextual and morphological features and nine data-sets of different genres and annotations. We measure the impact …

research product

Word sense disamibiguation combining conceptual distance, frequency and gloss

Word sense disambiguation (WSD) is the process of assigning a meaning to a word based on the context in which it occurs. The absence of sense tagged training data is a real problem for the word sense disambiguation task. We present a method for the resolution of lexical ambiguity which relies on the use of the wide-coverage noun taxonomy of WordNet and the notion of conceptual distance among concepts, captured by a conceptual density formula developed for this purpose. The formula we propose, is a generalised form of the Agirre-Rigau conceptual density measure in which many (parameterised) refinements were introduced and an exhaustive evaluation of all meaningful combinations was performed.…

research product

Consensus statement of the Italian society of pediatric allergy and immunology for the pragmatic management of children and adolescents with allergic or immunological diseases during the COVID-19 pandemic

AbstractThe COVID-19 pandemic has surprised the entire population. The world has had to face an unprecedented pandemic. Only, Spanish flu had similar disastrous consequences. As a result, drastic measures (lockdown) have been adopted worldwide. Healthcare service has been overwhelmed by the extraordinary influx of patients, often requiring high intensity of care. Mortality has been associated with severe comorbidities, including chronic diseases. Patients with frailty were, therefore, the victim of the SARS-COV-2 infection. Allergy and asthma are the most prevalent chronic disorders in children and adolescents, so they need careful attention and, if necessary, an adaptation of their regular…

research product

Inteligencia artificial y derecho: entre el mito y la realidad. La destrucción algorítmica de la humanidad

Los avances en Inteligencia Artificial y su conexión con la Administración de Justicia obligan a realizar un análisis pausado sobre las implicaciones de la progresiva incorporación de sistemas automatizados en el ámbito del reconocimiento de derechos. Sin unos fundamentos teóricos sólidos para comprender adecuadamente la nueva era de la información es posible incurrir en posicionamientos sesgados que impidan reconocer la contribución que la ciencia y la tecnología pueden ofrecer en favor de la protección y la garantía de los derechos.

research product

Overview of the Evalita 2014 SENTIment POLarity Classification Task

International audience; English. The SENTIment POLarity Classification Task (SENTIPOLC), a new shared task in the Evalita evaluation campaign , focused on sentiment classification at the message level on Italian tweets. It included three subtasks: subjectivity classification, polarity classification, and irony detection. SENTIPOLC was the most participated Evalita task with a total of 35 submitted runs from 11 different teams. We present the datasets and the evaluation methodology, and discuss results and participating systems. Italiano. Descriviamo modalit a e risultati della campagna di valutazione di sistemi di sentiment analysis (SENTIment POLarity Classification Task), proposta per la …

research product