A Holistic Natural Language Generation Framework for the Semantic Web

With the ever-growing generation of data for the Semantic Web comes an increasing demand for this data to be made available to non-semantic Web experts. One way of achieving this goal is to translate the languages of the Semantic Web into natural language. We present LD2NL, a framework for verbalizing the three key languages of the Semantic Web, i.e., RDF, OWL, and SPARQL. Our framework is based on a bottom-up approach to verbalization. We evaluated LD2NL in an open survey with 86 persons. Our results suggest that our framework can generate verbalizations that are close to natural languages and that can be easily understood by non-experts. Therewith, it enables non-domain experts to interpret Semantic Web data with more than 91\% of the accuracy of domain experts.

[1]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[2]  Jens Lehmann,et al.  Sorry, i don't speak SPARQL: translating SPARQL queries into natural language , 2013, WWW.

[3]  Halil Kilicoglu,et al.  Aligning Texts and Knowledge Bases with Semantic Sentence Simplification , 2016, WebNLG.

[4]  Elena Paslaru Bontas Simperl,et al.  SPARTIQULATION: Verbalizing SPARQL Queries , 2012, ILD@ESWC.

[5]  Richard Power,et al.  Expressing OWL axioms by English sentences: dubious in theory, feasible in practice , 2010, COLING.

[6]  Claire Gardent,et al.  The WebNLG Challenge: Generating Text from DBPedia Data , 2016, INLG.

[7]  Kathleen McKeown,et al.  Discourse Planning with an N-gram Model of Relations , 2015, EMNLP.

[8]  Daniel Duma,et al.  Generating Natural Language from Linked Data: Unsupervised template extraction , 2013, IWCS.

[9]  Claire Gardent,et al.  Building RDF Content for Data-to-Text Generation , 2016, COLING.

[10]  Philipp Cimiano,et al.  Exploiting Ontology Lexica for Generating Natural Language Texts from RDF Data , 2013, ENLG.

[11]  Claire Gardent,et al.  Generating Paraphrases from DBPedia using Deep Learning , 2016, WebNLG.

[12]  Jens Lehmann,et al.  SPARQL2NL: verbalizing sparql queries , 2013, WWW.

[13]  Jens Lehmann,et al.  DL-Learner - A framework for inductive learning on the Semantic Web , 2016, J. Web Semant..

[14]  Elena Paslaru Bontas Simperl,et al.  Labels in the Web of Data , 2011, SEMWEB.

[15]  Shashi Narayan,et al.  Creating Training Corpora for NLG Micro-Planners , 2017, ACL.

[16]  Hercules Dalianis,et al.  Aggregation in Natural Language Generation , 1999 .

[17]  Ion Androutsopoulos,et al.  Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System , 2013, J. Artif. Intell. Res..

[18]  Robert Stevens,et al.  The Manchester OWL Syntax , 2006, OWLED.

[19]  Andreas Harth,et al.  A language-independent method for the extraction of RDF verbalization templates , 2014, INLG.

[20]  H. Lan,et al.  SWRL : A semantic Web rule language combining OWL and ruleML , 2004 .

[21]  Tim Furche,et al.  deqa: Deep Web Extraction for Question Answering , 2012, SEMWEB.

[22]  Emiel Krahmer,et al.  Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation , 2017, J. Artif. Intell. Res..