Annotating Arabic Texts with Linked Data
| Autor: | Noureddine Doumi, Abdelghani Bouziane, Djelloul Bouchiha |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Vocabulary
Computer science business.industry media_common.quotation_subject 05 social sciences Unstructured data 02 engineering and technology Linked data Semantics Discoverability World Wide Web Knowledge base ComputingMethodologies_DOCUMENTANDTEXTPROCESSING 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences business Semantic Web Natural language 050104 developmental & child psychology media_common |
| Zdroj: | 2020 4th International Symposium on Informatics and its Applications (ISIA). |
| Popis: | The evolution of the traditional Web towards the semantic Web allows the machine to be a first-order citizen on the Web and increases discoverability of and accessibility to the unstructured data on the Web. This evolution enables the Linked Data technology to be used as background knowledge bases for unstructured data, notably the texts, available nowadays on the Web. For the Arabic language, the current situation is less brightness; the content of the Arabic language on the Web doesn't reflect the importance of this language. Given the fact that Arabic is one of the most important languages in the Web, and unfortunately it is under-resourced, so creating linguistic resources for it now is a necessity. Thus, we developed a linguistic approach for annotating Arabic textual corpus with Linked Data, especially DBpedia, which is Linked Open Data (LOD) extracted from Wikipedia. This approach uses natural language techniques to shedding light on Arabic text with Linked Open Data. The evaluation results of this approach are encouraging, despite the high complexity of our independent-domain knowledge base and the reduced resources in Arabic natural language processing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|