The document discusses several techniques for building ontologies and linking data including building multilingual lexical ontologies from unstructured data using techniques like cross-lingual links and topic models, building domain independent ontologies through crowd-sourcing or automatically, ontology mapping using corpus-based or translation approaches, maintaining privacy and resolving inconsistencies in linked data, coreference resolution across Ethiopian government datasets, developing semantic web search engines and query formulation for local languages, performing topic modeling on big data for applications like policy making and tourism, integrating different types of data sources, and resolving anaphora and word senses in local languages.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
51 views10 pages
Automatic Ontology Building
The document discusses several techniques for building ontologies and linking data including building multilingual lexical ontologies from unstructured data using techniques like cross-lingual links and topic models, building domain independent ontologies through crowd-sourcing or automatically, ontology mapping using corpus-based or translation approaches, maintaining privacy and resolving inconsistencies in linked data, coreference resolution across Ethiopian government datasets, developing semantic web search engines and query formulation for local languages, performing topic modeling on big data for applications like policy making and tourism, integrating different types of data sources, and resolving anaphora and word senses in local languages.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 10
Automatic Ontology Building
1. Building Multilingual Lexical Ontologies for Local
Languages from Unstructured/Semi-structured Corpora – Using cross-lingual Wikipedia links – From parallel/comparable corpora by topic models – Using data mining techniques over the unstructured text – Using machine translation
2. Building domain independent ontologies
• Crowd-sourcing approach • Manually • Automatically Ontology Localization 1. Adapting an ontology to a different cultural context – By translating the lexical layer of the ontology – Domain adaptation Ontology Mapping 1. Ontology Mapping – Corpus-based Approach – Linguistic enrichment – Translation based Approach – Multilingual semantic measures 2. Mapping ontology instances 3. Using machine translation Privacy, security and Data Quality in linked data •How can we maintain privacy in the web of data 1. Discovering data inconsistency Coreference Resolution
1. Entity Coreference in Ethiopian Open Government
Data 2. Linking Datasets 3. Increasing open data impacts Semantic Web Search Engine for Local Languages 1. Amharic 2. Afan Oromo 3. Tigrigna 4. Etc Semantic Web Query Formulation 1. Translating queries 2. Query expansion 3. Etc Topic Modeling
1. Topic Modeling in Big Data Environment
– For policy making – For tourism development 2. Opinion Mining from Heterogeneous Data Sources – Combination of unstructured, semi-structured, structured sources 3. Etc Data Integration
1. XML data integration
2. RDF data integration 3. Relational database integration 4. Information Integration from Heterogeneous Data Sources Anaphora Resolution