Mauro Castillo

G.: The TALP systems for disambiguating WordNet glosses

This paper describes the TALP systems presented at Senseval-3 task 12 “Word-Sense Disambigua-tion... more

Automatic acquisition of sense examples using exretriever

by german rigau, Jordi Turmo, and Mauro Castillo

IBERAMIA Workshop on …, 2004

A current research line for word sense disambiguation (WSD) focuses on the use of supervised mach... more A 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. This paper presents ExRetriever, a new software tool for automatically acquiring large sets of sense tagged examples from large collections of text and the Web. ExRetriever exploits the knowledge contained in large-scale knowledge bases (e.g., WordNet) to build complex queries, each of them characterising particular senses of a word. These examples can be used as training instances for supervised WSD algorithms.

Download

The talp systems for disambiguat-ing wordnet glosses

by Jordi Atserias and Mauro Castillo

... Mauro Castillo, Francis Real, Jordi Atserias ... This research has been partially funded by t... more

Evaluating large-scale Knowledge Resources across Languages

Recent Advances in Natural Language Processing - RANLP, 2000

This paper presents an empirical evaluation in a multilingual scenario of the semantic knowledge ... more This paper presents an empirical evaluation in a multilingual scenario of the semantic knowledge present on publicly available large-scale knowl- edge resources. The study covers a wide range of manually and automatically derived large-scale knowledge resources for English and Spanish. In order to establish a fair and neutral comparison, the knowledge resources are evaluated using the same method on two

Download

Automatic Acquisition of Sense Examples using ExRetriever

Language Resources and Evaluation, 2000

A current research line for word sense disambiguation (WSD) focuses on the use of supervised mach... more A 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. This paper presents ExRetriever, a new software tool for automatically acquiring large sets of sense tagged examples from large collections of text and the Web. ExRetriever

Download

Asignación automática de etiquetas de dominios en WordNet

Resumen: En este art culo se describe un procedimiento para asignar de forma autom atica etiqueta... more Resumen: En este art culo se describe un procedimiento para asignar de forma autom atica etiquetas de dominio a las glosas de WordNet. Una de las motivaciones principales del trabajo es enriquecer fuentes l exicas con informaci on de WordNet. Para ello, se utilizan los WordNet Domains. Finalmente, se proponen y corrigen etiquetas de dominios para la parte nominal y verbal de WordNet.

Download

A proposal for improving WordNet Domains

Automatic Assignment of Domain Labels to WordNet

by Mauro Castillo and german rigau

This paper describes a process to automatically assign domain labels to WordNet glosses. One of t... more This paper describes a process to automatically assign domain labels to WordNet glosses. One of the main goals of this work is to show different ways to enrich sistematically and automatically dictionary definitions (or gloses of new WordNet versions) with MultiWordNet domains. Finally, we show how this technique can be used to verify the consistency of the current version of MultiWordNet Domains. * This paper had partially financed by the European Comition (MEANING IST-2001-34460), Generalitat de Catalunya (2002FI 00648) y UTEM-Chile.

Download

A Graph-Based Method to Improve WordNet Domains

Lecture Notes in Computer Science, 2012

ABSTRACT

Multiwords and Word Sense Disambiguation

Lecture Notes in Computer Science, 2005

In the past years there has been a growing awareness of Multiword Expressions (MWEs). Due to thei... more

The TALP Systems for Disambiguating WordNet Glosses Mauro Castillo, Francis Real, Jordi Atserias TALP Research Center. UPC. Jordi Girona 1-3 08034 …

by Jordi Atserias and Mauro Castillo

acl.ldc.upenn.edu

... Mauro Castillo, Francis Real, Jordi Atserias TALP Research Center. UPC. ... In In Pr oceeding... more

The talp systems for disambiguating wordnet glosses

… of SENSEVAL-3 Third …, 2004

... Mauro Castillo, Francis Real, Jordi Atserias ... This research has been partially funded by t... more

The MEANING approach for automatic acquisition of sense examples

ExRetriever characterises each sense of a word as a specific query. This is automatically done by... more

SENSEVAL-3: Third International Workshop on the Evaluation of Systems

by Jordi Atserias and Mauro Castillo

... Adrian Novischi, Dan Moldovan, Paul Parker, Adriana Badulescu, Bob Hauser Language Computer C... more

Automatic acquisition of sense examples using exretriever

IBERAMIA Workshop on …, 2004

A current research line for word sense disambiguation (WSD) focuses on the use of supervised mach... more A 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. This paper presents ExRetriever, a new software tool for automatically acquiring large sets of sense tagged examples from large collections of text and the Web. ExRetriever exploits the knowledge contained in large-scale knowledge bases (e.g., WordNet) to build complex queries, each of them characterising particular senses of a word. These examples can be used as training instances for supervised WSD algorithms.

Download

Exploring large-scale acquisition of multilingual semantic models for predicates

by Jordi Atserias and Mauro Castillo

Resumen: Investigamos la posibilidad de obtener patrones sem anticos a gran escala para cualquier... more Resumen: Investigamos la posibilidad de obtener patrones sem anticos a gran escala para cualquier lengua usando solamente an alisis super cial y generalizaciones sem anticas b asicas. Siendo este un experimento exploratorio s olo hemos realizado una evaluaci on cualitativa. Hemos comparado varios patrones sem anticos de traducci on de verbos equivalentes en distintas lenguas y dominios.

Download

Uploads

Papers by Mauro Castillo

Log In