نویسندگان
1 دانشکده کامپیوتر؛ واحد تهران مرکزی؛ دانشگاه آزاد اسلامی؛ تهران، ایران
2 دانشکده کامپیوتر؛ دانشگاه علم و صنعت ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
The knowledge graph plays an important role in the Semantic Web and Natural Language Processing (NLP) tools. There are many knowledge bases in different languages, however lack of Farsi-specific knowledge base appears some defects in research and industrial applications. In this study, the most comprehensive knowledge base in Farsi language is presented, which consists of more than 500K of entities and 7 million relations, which is accessible in an open source repository. Data is supplied from four sources: Farsi Wikipedia and its structured data such as infoboxes, web tables, Wiki tables, and a relation extraction module. A variety of challenges of triple extraction from web tables, especially wiki tables, is addressed and some solutions to tackle these challenges are offered. According to the semantic web, RDF data model and OWL2 ontology employed to implement the Farsi Knowledge Graph (FKG). Resources and their relations are stored in triple format, therefor access to the knowledge graph is provided by a SPARQL endpoint. The FKG consists of several main parts including triple extraction from raw text, triple extraction from structured data, knowledge base creation, a search system on the knowledge base, and an entity linking module. In this paper, overall architecture of these parts is discussed in detail. One of the major contribution of this work is mapping of the ontology to the FarsNet, the Persian WordNet, for research purposes. In this graph, there are a large amount of information on a variety of topics including famous people, important places, organizations and companies, literary and art works, physiology, biology, events, species, astronomy, etc. For evaluation purposes, a small part of triples were randomly collected to build a test dataset for manually inspection. Experimental results demonstrate that more than 94% of triples were obtained correctly through the process of extraction, conversion, mapping, transformation and store. Future of internet according to the semantic web will be a complex and huge global knowledge base, therefor the FKG can play a significant role in developingthis emerging technology.
کلیدواژهها [English]
)