Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention

Semantic parsing is the process of mapping a natural language sentence into a formal representation of its meaning. In this work we use the neural network approach to transform natural language sentence into a query to an ontology database in the SPARQL language. This method does not rely on handcraft-rules, high-quality lexicons, manually-built templates or other handmade complex structures. Our approach is based on vector space model and neural networks. The proposed model is based in two learning steps. The first step generates a vector representation for the sentence in natural language and SPARQL query. The second step uses this vector representation as input to a neural network (LSTM with attention mechanism) to generate a model able to encode natural language and decode SPARQL.

[1]  Sébastien Ferré,et al.  Sparklis: An expressive query builder for SPARQL endpoints with guidance in natural language , 2016, Semantic Web.

[2]  Hiyan Alshawi,et al.  Deterministic Statistical Mapping of Sentences to Underspecified Semantics , 2011, IWCS.

[3]  I. Jolliffe.  Principal Component Analysis , 2002 .

[4]  Chong Wang,et al.  PANTO: A Portable Natural Language Interface to Ontologies , 2007, ESWC.

[5]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[6]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[7]  Jens Lehmann,et al.  AutoSPARQL: Let Users Query Your Knowledge Base , 2011, ESWC.

[8]  Christopher Potts,et al.  Recursive Neural Networks for Learning Logical Semantics , 2014, ArXiv.

[9]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[10]  Akiko Aizawa,et al.  An information-theoretic perspective of tf-idf measures , 2003, Inf. Process. Manag..

[11]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[12]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[13]  Navdeep Jaitly,et al.  Hybrid speech recognition with Deep Bidirectional LSTM , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[14]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[15]  Noah A. Smith,et al.  Recurrent Neural Network Grammars , 2016, NAACL.

[16]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[17]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[18]  Iyad AlAgha.  Using Linguistic Analysis to Translate Arabic Natural Language Queries to SPARQL , 2015, ArXiv.

[19]  Sébastien Ferré.  SQUALL: A Controlled Natural Language for Querying and Updating RDF Graphs , 2012, CNL.

[20]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[21]  Abraham Bernstein,et al.  Querix: A Natural Language Interface to Query Ontologies Based on Clarification Dialogs , 2006 .