Data Portal @ linkeddatafragments.org

ScholarlyData

Search ScholarlyData by triple pattern

Matches in ScholarlyData for { ?s ?p We present DEANNA, a framework for natural language question answering over structured knowledge bases. Given a natural language question, DEANNA translates questions into a SPARQL-like structured query language that can be evaluated over knowledge bases such as Yago, Dbpedia, Freebase, or other Linked Data sources.DEANNA analyzes questions and aims to map verbal phrases to relations and noun phrases to either individual entities or semantic classes. Importantly, it judiciously generates variables for target entities or classes to express joins between multiple triple patterns.In contrast to prior work on QA, we leverage the semantic type system for entities and we use constraints in jointly mapping the constituents of the question to relations, classes, and entities. We demonstrate the capabilities and interface of DEANNA, which allows advanced users to influence the translation process and view how the different components interact to produce the final result.. }

Showing items 1 to 1 of 1 with 100 items per page.