Recently, there is an increased interest on approaches, methodologies and tools converting natura... more Recently, there is an increased interest on approaches, methodologies and tools converting natural language into machine readable representations, such as RDF format. Although several steps have been made towards Natural Language Processing (NLP) domain, the machine intelligence for understanding natural language is still a topic of high research interest and its further exploration is going to bring significant benefits to several sub-tasks such as machine translation and questions answering. Natural language processing and natural language understanding are the usual approaches to transform the textual content from being unstructured and ambiguous, into structured and unambiguous. The current article presents the pipeline of linguistic processing and knowledge extraction techniques that are combined together in order to extract structured knowledge from natural language textual content and populate a knowledge base with quality triples. Moreover, it gives an overview of existing knowledge extraction tools found in the literature. Last, a short discussion and comparison of these tools is provided, and the article concludes with a brief summary.
Recently, there is an increased interest on approaches, methodologies and tools converting natura... more Recently, there is an increased interest on approaches, methodologies and tools converting natural language into machine readable representations, such as RDF format. Although several steps have been made towards Natural Language Processing (NLP) domain, the machine intelligence for understanding natural language is still a topic of high research interest and its further exploration is going to bring significant benefits to several sub-tasks such as machine translation and questions answering. Natural language processing and natural language understanding are the usual approaches to transform the textual content from being unstructured and ambiguous, into structured and unambiguous. The current article presents the pipeline of linguistic processing and knowledge extraction techniques that are combined together in order to extract structured knowledge from natural language textual content and populate a knowledge base with quality triples. Moreover, it gives an overview of existing knowledge extraction tools found in the literature. Last, a short discussion and comparison of these tools is provided, and the article concludes with a brief summary.
Uploads
Drafts on Web Intelligence by Olga Loia