Neural Machine Translation for Query Construction and Composition

Research on question answering with knowledge base has recently seen an increasing use of deep architectures. In this extended abstract, we study the application of the neural machine translation paradigm for question parsing. We employ a sequence-to-sequence model to learn graph patterns in the SPARQL graph query language and their compositions. Instead of inducing the programs through question-answer pairs, we expect a semi-supervised approach, where alignments between questions and queries are built through templates. We argue that the coverage of language utterances can be expanded using late notable works in natural language generation.

[1]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[2]  Jens Lehmann,et al.  Neural Network-based Question Answering over Knowledge Graphs on Word and Character Level , 2017, WWW.

[3]  Christophe Gravier,et al.  Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types , 2018, NAACL.

[4]  Sandro Rautenberg,et al.  DBtrends: Exploring Query Logs for Ranking RDF Data , 2016, SEMANTiCS.

[5]  Zhen Wang,et al.  Knowledge Graph and Text Jointly Embedding , 2014, EMNLP.

[6]  Iryna Gurevych,et al.  End-to-End Representation Learning for Question Answering with Weak Supervision , 2017, SemWebEval@ESWC.

[7]  Diego Esteves,et al.  SPARQL as a Foreign Language , 2017, SEMANTiCS.

[8]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[9]  E. Prud hommeaux,et al.  SPARQL query language for RDF , 2011 .

[10]  Jens Lehmann,et al.  Formal Query Generation for Question Answering over Knowledge Bases , 2018, ESWC.

[11]  Tiejun Zhao,et al.  Knowledge-Based Question Answering as Machine Translation , 2014, ACL.

[12]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[13]  Richard Socher,et al.  Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning , 2018, ArXiv.

[14]  Elena Cabrio,et al.  Question Answering over Linked Data (QALD-5) , 2014, CLEF.

[15]  Hua Wu,et al.  An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge , 2017, ACL.

[16]  Jens Lehmann,et al.  DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia , 2015, Semantic Web.

[17]  Gerhard Weikum,et al.  Automated Template Generation for Question Answering over Knowledge Graphs , 2017, WWW.

[18]  Enrico Motta,et al.  Evaluating question answering over linked data , 2013, J. Web Semant..

[19]  Nando de Freitas,et al.  Neural Programmer-Interpreters , 2015, ICLR.

[20]  Chen Liang,et al.  Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision , 2016, ACL.

[21]  Anja Jentzsch.  Linked Open Data Cloud , 2014 .

[22]  Gerhard Weikum,et al.  Never-Ending Learning for Open-Domain Question Answering over Knowledge Bases , 2018, WWW.

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.