<html><body><a href="http://infoling.org" target="_blank"><img
src="http://infoling.org/img/infoling.png" alt="Logo image by Hay
Kranen / CC-BY" width="255" height="50" align="left" border="0" /></a>
<br /><br /><br />
<br /><font style="font-size:80%"><table border="0" bordercolor="#FFF"
width="190px"><tr><td> </td><td> <a
style="text-decoration:none" href="http://www.facebook.com/infoling"
target="_blank"><img border="0"
src="http://infoling.org/img/facebook-icon.png" alt="Infoling at
Facebook" style="vertical-align:-30%;height:16px;width:16px" />
Facebook</a></td><td> <a style="text-decoration:none"
href="http://www.twitter.com/infoling" target="_blank"><img border="0"
src="http://infoling.org/img/t_small-b.png" alt="Infoling at Twitter"
style="vertical-align:-30%;height:16px;width:16px" />
Twitter</a></td></tr></table></font>
<br />Moderador/a: Carlos Subirats (U. Autónoma Barcelona), Mar Cruz
(U. Barcelona)
<br />Editoras: Paloma Garrido (U. Rey Juan Carlos), Laura Romero (UB)
<br />Programación, desarrollo: Marc Ortega (UAB)
<br />Directoras/es de reseñas: Alexandra Álvarez (U. Los Andes,
Venezuela), Yvette Bürki (U. Bern, Suiza), María Luisa Calero (U.
Córdoba, España), Luis Cortés (U. Almería)
<br />Asesoras/es: Isabel Verdaguer (UB), Gerd Wotjak (U. Leipzig,
Alemania)
<br />Colaboradoras/es: Julia Bernd (Cause Data Collective, EE.UU),
Antonio Ríos (UAB), Danica Salazar (UB)
<br />
<br />Con el patrocinio de:
<br /><table border="0" bordercolor="#FFFFFF"
width="200px"><tr><!--<td><a href="http://www.fundacioncomillas.es/"
target="_blank"><img
src="http://www.infoling.org/img/logo-comillas.png" alt="Fundación
Comillas" width="85" height="49" align="left" border="0"
/></a></td>--><td><a
href="http://www.arcomuralla.com/Arco/Shop/default.asp"
target="_blank"><img style="border:0;margin-top:10px"
src="http://www.infoling.org/img/logoarco.jpg" alt="Arco Libros"
width="62" height="34" align="left" border="0"
/></a></td></tr></table><br /><hr /><font style="font-size:90%">
<br /><b>Infoling 12.25 (2012)</b><br />ISSN: 1576-3404 </font>
<br /><font style="font-size:90%">© Infoling 1996-2012. Reservados
todos los derechos</font>
<br />
<br /><hr /><b>Tesis doctoral: </b><br />Pareja Lora, Antonio. 2012.
OntoTag. A Linguistic and Ontological Annotation Model Suitable for
the Semantic Web. Universidad Politécnica de Madrid (UPM) (España),
Departamento de Inteligencia Artificial (DIA).<br /><b>Tesis completa
en el Archivo de Infoling:</b> <a
href='http://www.infoling.org/repository/ID/95'
target='_blank'>http://www.infoling.org/repository/ID/95</a><br
/><b>Enlace externo</b>: <a href="http://oa.upm.es/13827/"
target="_blank">http://oa.upm.es/13827/</a><br /><b>Información
de:</b> Antonio Pareja Lora <apareja@sip.ucm.es><br />Compartir:
<a
href="http://api.addthis.com/oexchange/0.8/forward/facebook/offer?url=http://www.infoling.org/informacion/T95.html&pubid=ra-4def7f4a7565a706"
target="_blank" rel="nofollow"><img border="0"
src="http://infoling.org/img/facebook-icon.png" alt="Send to Facebook"
title="Send to Facebook"
style="vertical-align:-30%;height:16px;width:16px"
/></a> <a
href="http://api.addthis.com/oexchange/0.8/forward/twitter/offer?url=http://www.infoling.org/informacion/T95.html&template=@infoling%20Pareja,%20A.%20OntoTag%20{{url}}&pubid=ra-4def7f4a7565a706&shortener=bitly&bitly.login=infoling&bitly.apiKey=R_60e1d6b1cb688030e7759b835f63d0c0"
target="_blank" rel="nofollow"><img border="0"
src="http://infoling.org/img/t_small-b.png" alt="Tweet this"
title="Tweet this" style="vertical-align:-30%;height:16px;width:16px"
/></a><hr /><p><a
href="http://infoling.org/english/search/tesis/ID/95"
target="_blank">View with English headings</a></p><hr /><br
/><b>Director/a de tesis: </b>Guadalupe Aguado de Cea<br
/><b>Codirector/a: </b>Asunción Gómez Pérez<br /><br
/><b>Descripción</b><br /><p>El objeto principal de esta tesis es el
modelo de anotación OntoTag, de utilidad tanto para la Lingüística
como para la Web Semántica. El modelo OntoTag fue concebido cuando
aún (1) no se había publicado ningún estándar oficial de
anotación lingüística, (2) no se tenía claro qué es o puede
considerarse realmente una ontología, (3) no se había desarrollado
ninguna ontología lingüística, (4) no existían las primeras
recomendaciones del W3C para RDF y OWL, y (5) la Web Semántica era
aún una utopía. No obstante, desde un primer momento, este modelo de
anotación ya incorporaba todas estas tecnologías, por entonces
incipientes, [A] para combinar, integrar e interconectar anotaciones
de varios tipos y/o niveles, y también [B] para hacer que un conjunto
de herramientas y recursos lingüísticos interoperaran de manera
efectiva. Estos dos objetivos se alcanzaron gracias al conjunto de
ontologías lingüísticas que forman el núcleo principal del modelo.
OntoTag proporciona asimismo una metodología y un conjunto de buenas
prácticas para la anotación lingüística y ontológica de textos,
de acuerdo con las normas, recomendaciones y directrices de
anotaciones lingüísticas y para la Web Semántica publicadas hasta
la finalización de este trabajo de investigación. Finalmente, en la
presente tesis también se presenta la plataforma OntoTagger.
OntoTagger se desarrolló aplicando la metodología y el conjunto de
buenas prácticas ya mencionados para evaluar el modelo OntoTag. Los
resultados experimentales obtenidos mediante esta plataforma
permitieron confirmar y/o refutar las distintas hipótesis asociadas
al modelo de anotación. Todos estos resultados quedan recogidos
también en la memoria de la tesis.</p><br /><b>Área temática:</b>
Lingüística computacional, Lingüística de corpus, Semántica<br
/><br /><b>Índice</b><br /><p>1. Introduction<br />1.1. Linguistic
tools and annotations: their lights and shadows<br />1.1.1. The
lights: linguistic tools and annotations are very useful…<br
/>1.1.2. The shadows of linguistic tools and annotations<br
/>1.1.2.1 Linguistic tools are usually expensive<br
/>1.1.2.2 Sometimes, linguistic tools and annotations are not
accurate<br />1.1.2.3 Linguistic tools and linguistic annotations
hardly interoperate<br />1.2. The problem of linguistic tools and/or
annotations interoperation in detail<br />1.3. Solving the problem: an
outline of our proposal<br />1.3.1. The role of ontologies<br
/>1.3.2. The role of standardisation<br />1.3.3. A desideratum:
minimise cascaded errors<br />1.4. Our proposal: main pillars,
contributions and results<br />1.5. Structure of this dissertation<br
/><br />2. Work objectives<br />2.1. Open research problems<br
/>2.2. Goals of the present work<br />2.3. Expected contributions and
results<br />2.4. Work assumptions, hypotheses and restrictions<br
/>2.4.1. Assumptions<br />2.4.2. Hypotheses<br
/>2.4.3. Restrictions<br /><br />3. State of the art<br
/>3.1. Annotation: a historical approach and basic terminology<br
/>3.2. Annotation: current approaches<br />3.2.1. The linguistic
approach to annotation<br />3.2.1.1 Morphosyntactic annotations<br
/>3.2.1.2 Syntactic annotations<br />3.2.1.3 Semantic annotations<br
/>3.2.1.3.1 Semantic annotation layers<br />3.2.1.3.2 Semantic
annotation-related projects, guidelines and standardisation
initiatives<br />3.2.1.3.2.1 Regarding the Sense Tagging Layer<br
/>3.2.1.3.2.2 Regarding the Semantic Domain Annotation Layer<br
/>3.2.1.3.2.3 Regarding the Semantic Field Annotation Layer<br
/>3.2.1.3.2.4 Regarding the Semantic Role Labelling Layer<br
/>3.2.1.3.3 Semantic annotations – concluding remarks<br
/>3.2.1.4 Linguistic annotation: level-independent approaches<br
/>3.2.2. The computational approach to annotation<br
/>3.2.2.1 Computational representation of annotations: annotation
languages<br />3.2.2.2 The semantic web and semantic (web)
annotations<br />3.2.2.2.1 Definition of ontological tagsets and
metadata: RDFS and OWL<br />3.3. Concluding remarks: guidelines for a
hybrid approach to annotation<br /><br />4. OntoTag: the hybrid
annotation model<br />4.1. OntoTag’s linguistic ontologies<br
/>4.1.1. Building ontologies with methontology<br />4.1.2. The OntoTag
Integration Ontology (OIO)<br />4.1.2.1 OIO glossary of terms<br
/>4.1.2.2 OIO concept taxonomies<br />4.1.2.3 OIO ad hoc
relationships<br />4.1.2.4 OIO concept dictionary<br />4.1.2.5 OIO
detailed tables<br />4.1.2.5.1 OIO ad hoc binary relation table<br
/>4.1.2.5.2 OIO instance attribute table<br />4.1.2.5.3 OIO class
attribute table<br />4.1.2.5.4 OIO constant table<br />4.1.2.6 OIO
formal axioms and rules<br />4.1.2.6.1 OIO rule table<br
/>4.1.2.6.2 OIO formal axiom table<br />4.1.2.7 OIO instance table<br
/>4.1.2.8 The OIO statistics<br />4.1.3. The linguistic unit ontology
(LUO)<br />4.1.3.1 The concept linguistic unit, its subclasses and its
attributes<br />4.1.3.2 The syntactic module<br />4.1.3.2.1 The
syntactic module concepts and taxonomy<br />4.1.3.2.2 The syntactic
module attributes<br />4.1.3.2.3 The syntactic module ad hoc
relations<br />4.1.3.2.4 The syntactic module rules and axioms<br
/>4.1.3.3 The semantic module<br />4.1.3.3.1 The semantic module
concepts and taxonomy<br />4.1.3.3.2 The semantic module attributes<br
/>4.1.3.3.3 The semantic module ad hoc relations<br />4.1.3.3.4 The
semantic module rules and axioms<br />4.1.3.4 The LUO statistics<br
/>4.1.4. The linguistic attribute ontology (LAO)<br />4.1.4.1 The LAO
concepts, taxonomy and instances<br />4.1.4.1.1 Top-level concepts and
taxonomy in the LAO<br />4.1.4.1.2 Syntactic concepts, taxonomy and
instances in the LAO<br />4.1.4.1.3 Semantic concepts, taxonomy and
instances in the LAO<br />4.1.4.2 The LAO attributes<br />4.1.4.3 The
LAO ad hoc relations<br />4.1.4.4 The LAO rules and axioms<br
/>4.1.4.5 The LAO statistics<br />4.1.5. The linguistic value ontology
(LVO)<br />4.1.5.1 The LVO concepts, taxonomy and instances<br
/>4.1.5.1.1 Top-level concepts and taxonomy in the LVO<br
/>4.1.5.1.2 Syntactic concepts, taxonomy and instances in the LVO<br
/>4.1.5.1.3 Semantic concepts, taxonomy and instances in the LVO<br
/>4.1.5.2 The LVO attributes<br />4.1.5.3 The LVO ad hoc relations<br
/>4.1.5.4 The LVO rules and axioms<br />4.1.5.5 The LVO statistics<br
/>4.2. OntoTag’s abstract annotation architecture<br />4.2.1. Phase
1 – Distillation<br />4.2.2. Phase 2 – Tagging<br />4.2.3. Phase 3
– Standardisation<br />4.2.4. Phase 4 – Decanting<br
/>4.2.5. Phase 5 – Merging<br />4.2.5.1 Sub-Phase 5.1 –
Combination (Intra-Level Merging)<br />4.2.5.1.1 L+POS Combination<br
/>4.2.5.1.2 POS+M Combination<br />4.2.5.1.3 Syntactic Combination<br
/>4.2.5.1.4 Semantic Combination<br />4.2.5.2 Sub-Phase 5.2 –
Integration (Inter-Level Merging)<br />4.2.5.3 Putting combination and
integration together<br />4.3. OntoTag’s abstract annotation
scheme<br />4.3.1.1 Morphosyntactic annotations<br />4.3.1.2 Other
annotations at the Syntactic Level<br />4.3.1.3 Annotations at the
Semantic Level<br />4.3.1.3.1 Annotations at the Concept Semantic
Annotation Layer<br />4.3.1.3.2 Annotations at the Instance Semantic
Annotation Layer<br /><br />5. OntoTagger: an instance of OntoTag<br
/>5.1. Linguistic annotation tools integrated into OntoTagger<br
/>5.1.1. Connexor’s FDG (Functional Dependency Grammar) Parser for
Spanish<br />5.1.2. Bitext’s Datalexica<br />5.1.3. LACELL’s POS
Tagger<br />5.2. OntoTagger’s configuration components<br />5.3. The
Combination Module (MMACM) in detail<br />5.3.1. Syntactic structure
combination<br />5.3.2. Morphosyntactic category and lemma
combination<br />5.3.2.1 Morphosyntactic category combination<br
/>5.3.2.1.1 Mathematical terms applied in the notation<br
/>5.3.2.1.2 Description of the notation<br />5.3.2.1.3 Morphosyntactic
category combination rules<br />5.3.2.2 Lemma combination<br
/>5.3.2.2.1 Mathematical terms applied in the notation<br
/>5.3.2.2.2 Description of the notation<br />5.3.2.2.3 Lemma
combination rules<br />5.3.3. Morphological combination<br
/>5.3.3.1 Mathematical terms applied in the notation<br
/>5.3.3.2 Description of the notation<br />5.3.3.3 Morphological
combination rules<br />5.4. The Semantic Annotation Manager Module
(SAMM) in detail<br />5.4.1. OntoTaggerLex – the semantic lexicon<br
/>5.4.2. The Instance Semantic Annotation Layer<br />5.4.2.1 Named
entity-related linguistic heuristics<br />5.4.2.1.1 Description of the
notation<br />5.4.2.1.2 Rules for named entity recognition<br
/>5.4.2.1.2.1 Rules for simple named entity identification<br
/>5.4.2.1.2.2 Rules for multiword named entity aggregation<br
/>5.4.2.1.3 Rules for named entity (sub)classification<br />5.4.3. The
concept semantic annotation layer<br />5.4.3.1 Domain–Independent
Sense Tagging: EuroWordNet integration<br />5.4.3.2 Domain–Dependent
Sense Tagging: CNEO integration<br />5.4.4. Putting semantic
annotations together: the Semantic Intra-Level Merger (SILM)<br
/>5.4.5. The semantic learning process<br />5.5. OntoTagger’s
annotation schemas<br />5.5.1. XML implementation: an example<br
/>5.5.2. OWL implementation: an example<br /><br />6. Results and
evaluation<br />6.1. Evaluation of the combination sub-phase<br
/>6.1.1. Statistical analysis of the morphosyntactic category
combination results<br />6.1.1.1 Precision-related (generic)
statistical indicators<br />6.1.1.2 Recall-related (particular)
statistical indicators<br />6.1.2. Statistical analysis of the lemma
combination results<br />6.1.3. Statistical analysis of the
morphological attribute combination results<br />6.2. Evaluation of
the named entity recognition and classification subsystem<br /><br
/>7. Conclusions<br />7.1. Main outcomes<br />7.2. Other practical
outcomes<br />7.2.1. Recommendations, best practices and lessons
learned for annotation standardisation, interoperation and merge<br
/>7.3. Other theoretical outcomes<br />7.3.1. Concerning
standardisation<br />7.3.2. Concerning annotation interoperation and
merge<br />7.4. OntoTag’s hypotheses assessment<br /><br
/>8. Further work<br />9. Acknowledgements<br />10. References<br
/>11. Appendix A: OntoTagger’s annotation XML schema</p><br
/><b>Fecha de lectura o defensa:</b> 26 de julio de 2012<br /><br
/><b>Número de págs.:</b> 365<br /><br /><b>Correo-e del
autor/a:</b> <apareja@sip.ucm.es><br /><br /><b>Información en
la web de Infoling:</b><br /> <a
href="http://www.infoling.org/informacion/T95.html" target="_blank">
http://www.infoling.org/informacion/T95.html</a></body></html>