In this paper we present a demonstration of a multilingual generalization of Word-Class Lattices (WCLs), a supervised lattice-based model used to identify textual definitions and extract hypernyms from them. Lattices are learned from a dataset of automatically-annotated definitions from Wikipedia. We release a Java API for the programmatic use of multilingual WCLs in three languages (English, French and Italian), as well as a Web application for definition and hypernym extraction from user-provided sentences.
A Java Framework for Multilingual Definition and Hypernym Extraction / Faralli, Stefano; Navigli, Roberto. - STAMPA. - (2013), pp. 103-108. (Intervento presentato al convegno ACL 2013 tenutosi a Sofia, Bulgaria nel August 4-9, 2013).
A Java Framework for Multilingual Definition and Hypernym Extraction
FARALLI, Stefano;NAVIGLI, ROBERTO
2013
Abstract
In this paper we present a demonstration of a multilingual generalization of Word-Class Lattices (WCLs), a supervised lattice-based model used to identify textual definitions and extract hypernyms from them. Lattices are learned from a dataset of automatically-annotated definitions from Wikipedia. We release a Java API for the programmatic use of multilingual WCLs in three languages (English, French and Italian), as well as a Web application for definition and hypernym extraction from user-provided sentences.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
