Neural SPARQL Machines: Translating natural language into machine language for data access.

  • screenshot

Neural SPARQL Machines translate natural language expressions into sequences encoding SPARQL queries. A generator module builds the training set from manually- or automatically-created templates and a knowledge base. The tasks of entity recognition and query construction are entirely assigned to a LSTM-based recurrent neural network. The support for external word embeddings helps tackling the vocabulary mismatch problem, while curriculum learning is employed to learn graph pattern compositions.

@Twitter Issues Mailing List Source Code

In the last years, the Linked Data Cloud has achieved a size of more than 100 billion facts pertaining to a multitude of domains. However, accessing this information has been significantly challenging for lay users. Approaches to problems such as Question Answering on Linked Data and Link Discovery have notably played a role in increasing information access. These approaches are often based on handcrafted and/or statistical models derived from data observation. Recently, Deep Learning architectures based on Neural Networks called seq2seq have shown to achieve the state-of-the-art results at translating sequences into sequences. In this direction, we propose Neural SPARQL Machines, end-to-end deep architectures to translate any natural language expression into sentences encoding SPARQL queries. Our preliminary results, restricted on selected DBpedia classes, show that Neural SPARQL Machines are a promising approach for Question Answering on Linked Data, as they can deal with known problems such as vocabulary mismatch and perform graph pattern composition.


by (Editors: ) [BibTex of ]


No recent news available.