New Trends of Research in Ontologies and Lexical Resources Ideas, Projects, Systems
Surveying new directions of research and development in the interdisciplinary framework where ontologies and lexical resources intersect, this book deals with the complex relation between lexicons (in different languages) and the underlying ontological model.
Saved in:
| Main Authors | , , , |
|---|---|
| Format | eBook |
| Language | English |
| Published |
Berlin, Heidelberg
Springer Berlin / Heidelberg
2013
Springer Berlin Heidelberg Springer |
| Edition | 1 |
| Series | Theory and Applications of Natural Language Processing |
| Subjects | |
| Online Access | Get full text |
| ISBN | 9783642437786 3642437788 3642317812 9783642317811 |
| ISSN | 2192-032X 2192-0338 |
| DOI | 10.1007/978-3-642-31782-8 |
Cover
Table of Contents:
- Intro -- New Trends of Research in Ontologies and Lexical Resources -- Contents -- List of Figures -- Chapter 1 Introduction -- Part I Achieving the Interoperability of Linguistic Resources in the Semantic Web -- Chapter 2 Towards Open Data for Linguistics: Linguistic Linked Data -- 2.1 Motivation and Overview -- 2.2 Modelling Linguistic Resources as Linked Data -- 2.2.1 Modelling Lexical-Semantic Resources: WordNet -- 2.2.1.1 WordNet Data Structures -- 2.2.1.2 Generic Data Structures: Lexical Markup Framework -- 2.2.1.3 From LMF to RDF: lemon -- 2.2.2 Modelling Annotated Corpora: MASC -- 2.2.2.1 The Manually Annotated Sub-Corpus -- 2.2.2.2 Generic Data Structures for Annotated Corpora: GrAF -- 2.2.2.3 From Standoff XML to RDF: POWLA -- 2.3 Benefits of Linked Data for Linguistics -- 2.3.1 Structural Interoperability -- 2.3.1.1 Structural Interoperability by Content Negotiation -- 2.3.1.2 RDF as a Structurally Interoperable Format -- 2.3.2 Linking and Federation -- 2.3.3 Conceptual Interoperability -- 2.3.4 Ecosystem -- 2.3.5 Dynamic Import -- 2.4 Community Efforts Towards Lexical Linked Data -- 2.4.1 The Open Linguistics Working Group -- 2.4.2 W3C Ontology-Lexica Community Group -- 2.5 Summary -- References -- Chapter 3 Establishing Interoperability Between Linguistic and Terminological Ontologies -- 3.1 Introduction -- 3.2 Linguistic Knowledge -- 3.3 Networking Linguistic Ontologies -- 3.4 Related Work -- 3.5 LingNet -- 3.5.1 The LingNet Model -- 3.5.2 LingNet Implementation -- 3.6 Discussion -- 3.7 Conclusion and Future Work -- References -- Chapter 4 On the Role of Senses in the Ontology-Lexicon -- 4.1 Introduction -- 4.2 Senses: Universal or Context-Specific? -- 4.3 Senses in the Ontology-Lexicon Interface -- 4.3.1 Senses as Reification -- 4.3.2 Sense as Subset of Uses -- 4.3.3 Sense as a Subconcept -- 4.3.4 The Three Facets
- 4.4 Systematic Polysemy in the Ontology-Lexicon Interface -- 4.5 Senses in the Ontology-Lexicon Model Lemon -- 4.5.1 Sense Properties -- 4.5.2 Contexts and Conditions -- 4.5.3 Sense Relations -- 4.6 Conclusions -- References -- Part II Event Analysis from Text and Multimedia -- Chapter 5 KYOTO: A Knowledge-Rich Approach to the Interoperable Mining of Events from Text -- 5.1 Introduction -- 5.2 Packaging of Events -- 5.3 KYOTO Overview -- 5.4 Ontological and Lexical Background Knowledge -- 5.4.1 Ontology -- 5.4.2 Wordnet to Ontology Mappings -- 5.5 Off-Line Reasoning and Ontological Tagging -- 5.6 Event Extraction -- 5.7 Experimental Results -- 5.7.1 In-Depth Evaluation -- 5.7.2 Large Scale Evaluation -- 5.7.3 Transferring to Another Language -- 5.8 Conclusion -- References -- Chapter 6 Anchoring Background Knowledge to Rich Multimedia Contexts in the KnowledgeStore -- 6.1 Introduction -- 6.2 State of the Art -- 6.3 The KnowledgeStore Approach -- 6.3.1 Representation Layers -- 6.3.2 Content Processing -- 6.4 System Implementation -- 6.4.1 KnowledgeStore Core -- 6.4.2 Resource Preprocessing -- 6.4.3 Mention Extraction -- 6.4.4 Coreference Resolution -- 6.4.5 Mention-Entity Linking -- 6.4.6 Entity Creation and Enrichment -- 6.5 Experiments and Results -- 6.5.1 KnowledgeStore Population -- 6.5.2 Entity-Based Search -- 6.5.3 Contextualized Semantic Enrichment -- 6.6 Conclusions and Future Work -- References -- Chapter 7 Lexical Mediation for Ontology-Based Annotation of Multimedia -- 7.1 Introduction -- 7.2 Related Work -- 7.3 Case Study: Annotating Stories in Video -- 7.4 Accessing Large Scale Commonsense Knowledge Through a Lexical Interface -- 7.4.1 The Architecture of CADMOS -- 7.4.2 The Meaning Negotiation Process -- 7.5 Annotation Test and Discussion -- 7.5.1 Experimental Setting -- 7.5.2 Results and Discussion -- 7.6 Conclusion -- References
- Chapter 8 Knowledge in Action: Integrating Cognitive Architectures and Ontologies -- 8.1 Introduction -- 8.2 Knowledge Mechanisms Meet Contents in Visual Intelligence -- 8.2.1 Mechanisms: Cognitive Architectures as Modules of Knowledge Production -- 8.2.2 Contents: Ontologies as Declarative Knowledge Resources -- 8.2.3 Human Visual Intelligence -- 8.3 Making Sense of Visual Data -- 8.3.1 HOMinE: Model and Implementation -- 8.3.2 The Cognitive Engine -- 8.3.3 Recognition Task -- 8.3.4 Description Task -- 8.4 Evaluation -- 8.5 Conclusions and Future Work -- References -- Part III Enhancing NLP with Ontologies -- Chapter 9 Use of Ontology, Lexicon and Fact Repository for Reference Resolution in Ontological Semantics -- 9.1 Introduction -- 9.2 Our View of Reference Resolution Versus Others -- 9.3 The OntoAgent Environment and Its Resources -- 9.3.1 Comparing OntoAgent Static Knowledge Resources with Others -- 9.3.2 The OntoSem Text Analyzer -- 9.4 The Reference Resolution Algorithm -- 9.4.1 Stage 1: Proper Name Analysis During Preprocessing -- 9.4.2 Stage 2: Detection of Potentially Missing Elements in the Syntactic Parse -- 9.4.3 Stage 3: Reference Processing During Basic Semantic Analysis -- 9.4.3.1 Lexically Supported Detection and Analysis of Non-referring Expressions -- 9.4.3.2 Lexically Supported Detection (and Resolution) of Ellipsis -- 9.4.4 Stage 4: Running Lexically Recorded Meaning Procedures -- 9.4.5 Stage 5: Dedicated Reference Resolution Module -- 9.4.5.1 Resolve Referential Definite Descriptions: NP-Def -- 9.4.5.2 Resolve Proper Nouns -- 9.4.5.3 Resolve Indefinite NPs: NP-Indef -- 9.4.5.4 Resolve Bare NPs: NP-Bare -- 9.4.5.5 Resolve Third Person Pronouns -- 9.4.5.6 Resolve Referential Verbs -- 9.5 Final Thoughts: Semantics in Reference Resolution -- References -- Chapter 10 Ontology-Based Semantic Interpretation via GrammarConstraints
- 10.1 Introduction -- 10.2 Lexicalized Well-Founded Grammar -- 10.2.1 Semantic Molecule: A Syntactic-Semantic Representation -- 10.2.2 Semantic Composition and Interpretation as Grammar Constraints -- 10.2.3 LWFG Learning Model -- 10.3 Ontology-Based Semantic Interpretation -- 10.3.1 Levels of Representation -- 10.3.2 The Local Ontology-Based Semantic Interpreter -- 10.3.3 Global Semantic Interpreter -- 10.4 Knowledge Acquisition and Querying Experiments -- 10.4.1 Acquisition of Terminological Knowledge from Consumer Health Definitions -- 10.4.2 Natural Language Querying -- 10.5 Ambiguity Handling -- 10.6 Conclusions -- References -- Chapter 11 How Ontology Based Information Retrieval Systems May Benefit from Lexical Text Analysis -- 11.1 Introduction -- 11.2 Related Work -- 11.2.1 Conceptual Versus Keyword-Based IRSs -- 11.2.2 Hybrid Ontology Based Information Retrieval System -- 11.2.2.1 Hybrid Relevance Model -- 11.2.2.2 Hybrid Approach for User Interaction Improvement -- 11.2.2.3 Ontology and Lexical Resources Interfacing -- 11.2.3 Concept Identification Through Lexical Analysis -- 11.3 Concept Identification Through Lexical Analysis: The ``Synopsis'' Approach -- 11.3.1 Concept Characterization -- 11.3.1.1 Acquisition of Relevant Corpus -- 11.3.1.2 Significant Word Training -- 11.3.1.3 Representativity of Words -- 11.3.1.4 Lexicon Elaboration -- 11.3.2 Thematic Extraction -- 11.4 Human Accessibility Enhanced at the Crossroads of Ontology and Lexicology -- 11.4.1 An Example of Concept-Based IRS: OBIRS -- 11.4.2 Ontology and Lexical Resource Interfacing Within Hybrid IRSs -- 11.5 Evaluation: User Feedback on a Real Case Study -- 11.6 Conclusion and Perspectives -- References -- Part IV Sentiment Analysis Thorugh Lexicon and Ontologies -- Chapter 12 Detecting Implicit Emotion Expressions from Text Using Ontological Resources and Lexical Learning
- 12.1 Introduction -- 12.2 Related Work -- 12.2.1 Appraisal Theories -- 12.2.2 Affect Detection and Classification in Natural Language Processing -- 12.2.3 Knowledge Bases for NLP Applications -- 12.2.4 Lexical Learning -- 12.2.5 Linking Ontologies with Lexical Resources -- 12.3 The EmotiNet Knowledge Base -- 12.3.1 Self-Reported Affect and the ISEAR Data Set -- 12.3.2 Building the EmotiNet Knowledge Base -- 12.3.3 Preliminary Extensions of EmotiNet -- 12.4 Further Extensions of EmotiNet with Lexical and Ontological Resources -- 12.4.1 Extending EmotiNet with Additional Emotion-Triggering Situations -- 12.4.2 Extending EmotiNet Using Ontopopulis -- 12.5 Evaluation -- 12.6 Discussion, Conclusions and Future Work -- References -- Chapter 13 The Agile Cliché: Using Flexible Stereotypes as Building Blocks in the Construction of an Affective Lexicon -- 13.1 Introduction -- 13.2 Related Work and Ideas -- 13.3 Finding Stereotypes on the Web -- 13.3.1 Web-derived Models of Typical Behavior -- 13.3.2 Mutual Reinforcement Among Properties -- 13.4 Estimating Lexical Affect -- 13.5 In the Mood for Affective Search -- 13.6 Empirical Evaluation -- 13.6.1 Bottom Level: Properties and Behaviorsof Stereotypes -- 13.6.2 Top Level: Stereotypical Concepts -- 13.6.3 Separating Words by Affect: Two Views -- 13.7 Conclusions -- References -- Index