Multilingual Natural Language Interaction with Semantic Web Knowledge Bases and Linked Open Data

Controlled Natural Language

“…It has also been demonstrated that CNL can serve as an efficient and user-friendly interface for Big Data end-point querying [4; 5], or for bootstrapping robust NL interfaces [6]. as well as for tailored multilingual natural language generation from the retrieved data [4].…”

Survey on challenges of Question Answering in the Semantic Web

“…Damova et al [39] return well formulated natural language sentences that are created using a template with optional parameters for the domain of paintings. Between the input query and the SPARQL query, the system places the intermediate step of a multilingual description using the Grammatical Framework [116], which enables the system to support 15 languages.…”

Question answering over biomedical linked data with Grammatical Framework

“…The first step in using GF for querying linked data is to create support for the language SPARQL. From our knowledge, even though there are applications of GF for this task [3], GF libraries do not include resources for SPARQL.…”

“…One of the greatest challenges of this new big set of data is querying it. In order to fill the gap between end users and formal languages like SPARQL, more approaches emerged: querying in full natural language [18], or in Controlled Natural Languages [3], [7], [5], or incremental query building [17].…”

“…The starting point is the relation between the meaning of expressions in natural language and the constructors of description logics. This relation is also analyzed in [7], while GF is also used for linked data in [3], [4]. The targeted linked data are biomedical data, described in Diseasome, Sider and Drugbank.…”