Learning Methods and Algorithms for Semantic Text Classification across Multiple Domains

Pasolini, Roberto (2015) Learning Methods and Algorithms for Semantic Text Classification across Multiple Domains, [Dissertation thesis], Alma Mater Studiorum Università di Bologna. Dottorato di ricerca in Ingegneria elettronica, informatica e delle telecomunicazioni, 27 Ciclo. DOI 10.6092/unibo/amsdottorato/7058.
Documenti full-text disponibili:
[img]
Anteprima
Documento PDF (English) - Richiede un lettore di PDF come Xpdf o Adobe Acrobat Reader
Download (1MB) | Anteprima

Abstract

Information is nowadays a key resource: machine learning and data mining techniques have been developed to extract high-level information from great amounts of data. As most data comes in form of unstructured text in natural languages, research on text mining is currently very active and dealing with practical problems. Among these, text categorization deals with the automatic organization of large quantities of documents in priorly defined taxonomies of topic categories, possibly arranged in large hierarchies. In commonly proposed machine learning approaches, classifiers are automatically trained from pre-labeled documents: they can perform very accurate classification, but often require a consistent training set and notable computational effort. Methods for cross-domain text categorization have been proposed, allowing to leverage a set of labeled documents of one domain to classify those of another one. Most methods use advanced statistical techniques, usually involving tuning of parameters. A first contribution presented here is a method based on nearest centroid classification, where profiles of categories are generated from the known domain and then iteratively adapted to the unknown one. Despite being conceptually simple and having easily tuned parameters, this method achieves state-of-the-art accuracy in most benchmark datasets with fast running times. A second, deeper contribution involves the design of a domain-independent model to distinguish the degree and type of relatedness between arbitrary documents and topics, inferred from the different types of semantic relationships between respective representative words, identified by specific search algorithms. The application of this model is tested on both flat and hierarchical text categorization, where it potentially allows the efficient addition of new categories during classification. Results show that classification accuracy still requires improvements, but models generated from one domain are shown to be effectively able to be reused in a different one.

Abstract
Tipologia del documento
Tesi di dottorato
Autore
Pasolini, Roberto
Supervisore
Co-supervisore
Dottorato di ricerca
Scuola di dottorato
Scienze e ingegneria dell'informazione
Ciclo
27
Coordinatore
Settore disciplinare
Settore concorsuale
Parole chiave
text mining, text categorization, cross-domain text categorization,
URN:NBN
DOI
10.6092/unibo/amsdottorato/7058
Data di discussione
14 Aprile 2015
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza la tesi

^