Exploració per autor "Rigau Claramunt, German"
Ara es mostren els items 1-20 de 34
-
A Proposal for word sense disambiguation using conceptual distance
(1996-02-01)
Report de recerca
Accés obertThis paper presents a method for the resolution of lexical ambiguity and its automatic evaluation over the Brown Corpus. The method relies on the use of the wide-coverage noun taxonomy of WordNet and the notion of ... -
Acquisition of lexical translation relations from MRDs
(1994-09)
Report de recerca
Accés obertIn this paper we present a methodology for extracting information about lexical translation equivalences from the machine readable versions of conventional dictionaries (MRDs), and describe a series of experiments on ... -
An environment for management and extraction of taxonomies from on-line dictionaries
(1991-06)
Report de recerca
Accés obert -
An Experiment on automatic semantic tagging of dictionary senses
(1995-06)
Report de recerca
Accés obertWe present a methodology to enrich a dictionary sense with semantic tags. The method relies on the use of a wide-coverage noun taxonomy and the notion of conceptual distance among concepts. Some experimental results about ... -
Applying automatic methods for the construction of multilingual WordNets
(1998-02)
Report de recerca
Accés obert -
Automatic acquisition of sense examples using Exretriever
(2004)
Text en actes de congrés
Accés obertA current research line for word sense disambiguation (WSD) focuses on the use of supervised machine learning techniques. One of the drawbacks of using such techniques is that previously sense annotated data is required. ... -
Automatically extracting translation links using a wide coverage semantic taxonomy
(1995-01-01)
Report de recerca
Accés obertTGE (Tlink Generator Environment) is a system for semi-automatically extracting translation links. The system was developed within the ACQUILEX II project as a tool for supporting the construction of a multi-lingual lexical ... -
Bases de conocimiento multilíngües para el procesamiento semántico a gran escala
(2008-04)
Article
Accés obertEste artículo presenta el resultado del estudio de un amplio conjunto de bases de conocimiento multilingües actualmente disponibles que pueden ser de interés para un gran número de tareas de procesamiento semántico a gran ... -
Boosting applied to word sense disambiguation
(2000-01)
Report de recerca
Accés obertIn this paper we apply Schapire and Singer's AdaBoost.MH boosting algorithm to the Word Sense Disambiguation (WSD) problem. Initial experiments on a set of 15 selected polysemous words show that the boosting approach ... -
Combining Wikipedia and WordNet for improving domain terms compilation
(2013)
Report de recerca
Accés obertDomain terms are a useful mean for tuning both resources and NLP processors to domain specific tasks. This paper proposes an improved method for obtaining terms from potentially any domain using the Wikipedia graph structure ... -
Converting the Enciclopedia Catalana bilingual MRD to an MTD
(1998-02)
Report de recerca
Accés obert -
Dos aproximaciones a la adquisición del conocimiento léxico y conceptual para sistemas de procesamiento del lenguaje natural
(1991-11-06)
Report de recerca
Accés obertProcessament del llenguatge natural -
Evaluating large-scale knowledge resources across languages
(2007)
Text en actes de congrés
Accés obertThis paper presents an empirical evaluation in a multilingual scenario of the semantic knowledge present on publicly available large-scale knowledge resources. The study covers a wide range of manually and automatically ... -
Experiments on applying relaxation labeling to map multilingual hierarchies
(1999-02)
Report de recerca
Accés obertThis paper explores the automatic construction of a multilingual Lexical Knowledge Base from preexisting lexical resources. This paper presents a new approach for linking already existing hierarchies. The Relaxation ... -
Highlighting relevant concepts from Topic Signatures
(2012)
Text en actes de congrés
Accés obertThis paper presents deepKnowNet, a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method applies a knowledge-based Word Sense Disambiguation ... -
Integrating a large domain ontology of species into WordNet
(2010)
Text en actes de congrés
Accés restringit per política de l'editorialWith the proliferation of applications sharing information represented in multiple ontologies, the development of automatic methods for robust and accurate ontology matching will be crucial to their success. Connecting and ... -
KNOW: Developing large-scale multilingual technologies for language understanding
(2009-09)
Article
Accés obertEl proyecto KNOW pretende añadir significado, conocimiento y razonamiento a las tecnologías actuales de Procesamiento del Lenguaje Natural. -
KnowNet: A proposal for building highly connected and dense knowledge bases from the web
(2008)
Text en actes de congrés
Accés obertThis paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate nowledge-based Word Sense ... -
KnowNet: building a large net of knowledge from the web
(2008)
Text en actes de congrés
Accés obertThis paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense ... -
LDB/LKB integration
(1994-08)
Report de recerca
Accés obertThe Lexical Data Base (LDB) and the Lexical Knowledge Base (LKB) have played, as software systems, a core role within Acquilex I Esprit 3030 project. Main limitations were derived from the fact that the LDB and the LKB are ...
