Overcoming Challenges of Semantic Question Answering in the Semantic Web

Semantic Question Answering (SQA) removes two major access requirements to the Semantic Web: the mastery of a formal query language like SPARQL and knowledge of a specific vocabulary. Because of the complexity of natural language, SQA presents difficult challenges and many research opportunities. Instead of a shared effort, however, many essential components are redeveloped, which is an inefficient use of researcher's time and resources. This survey analyzes 62 different SQA systems, which are systematically and manually selected using predefined inclusion and exclusion criteria, leading to 70 selected publications out of 1960 candidates. We identify common challenges, structure solutions, and provide recommendations for future systems. This work is based on publications from the end of 2010 to July 2015 and is also compared to older but similar surveys.

[1]  Sören Auer,et al.  Query Segmentation and Resource Disambiguation Leveraging Background Knowledge , 2012, WoLE@ISWC.

[2]  Yuzhong Qu,et al.  RELIN: Relatedness and Informativeness-Based Centrality for Entity Summarization , 2011, International Semantic Web Conference.

[3]  Pierre Zweigenbaum,et al.  Medical question answering: translating medical questions into sparql queries , 2012, IHI '12.

[4]  Philipp Cimiano,et al.  Applying Semantic Parsing to Question Answering Over Linked Data: Addressing the Lexical Gap , 2015, NLDB.

[5]  Hamish Cunningham,et al.  FREyA: An Interactive Way of Querying Linked Data Using Natural Language , 2011, ESWC Workshops.

[6]  German Rigau,et al.  Book Reviews: EuroWordNet: A Multilingual Database with Lexical Semantic Networks , 1999, CL.

[7]  Rudi Studer,et al.  The Semantic Web: Research and Applications , 2004, Lecture Notes in Computer Science.

[8]  Fabien L. Gandon,et al.  The Semantic Web: Trends and Challenges , 2014, Lecture Notes in Computer Science.

[9]  Seonyeong Park,et al.  Question Answering System using Multiple Information Source and Open Type Answer Merge , 2015, HLT-NAACL.

[10]  Sören Auer,et al.  LIMES - A Time-Efficient Approach for Large-Scale Link Discovery on the Web of Data , 2011, IJCAI.

[11]  Mariana Damova,et al.  Mapping the central LOD ontologies to PROTON upper-level ontology , 2010, OM.

[12]  Hui Fang,et al.  Wikimantic: Disambiguation for Short Queries , 2012, NLDB.

[13]  Andreas Abecker,et al.  KOIOS: Utilizing Semantic Search for Easy-Access and Visualization of Structured Environmental Data , 2011, SEMWEB.

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

[15]  Gerhard Weikum,et al.  Deep answers for naturally asked questions on the web of data , 2012, WWW.

[16]  Aarne Ranta,et al.  Natural Language Interaction with Semantic Web Knowledge Bases and LOD , 2013 .

[17]  Paul Buitelaar,et al.  Towards Linguistically Grounded Ontologies , 2009, ESWC.

[18]  Evgeniy Gabrilovich,et al.  Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis , 2007, IJCAI.

[19]  Günter Neumann,et al.  The QALL-ME Framework: A specifiable-domain multilingual Question Answering architecture , 2011, J. Web Semant..

[20]  Ollivier Haemmerlé,et al.  SWIP at QALD-3: Results, Criticisms and Lesson Learned , 2013, CLEF.

[21]  Dirk Krechel,et al.  A German Natural Language Interface for Semantic Search , 2012, JIST.

[22]  Amit P. Sheth,et al.  Ontology Alignment for Linked Open Data , 2010, SEMWEB.

[23]  Fabien L. Gandon,et al.  QAKiS @ QALD-2 , 2012, ILD@ESWC.

[24]  Jens Lehmann,et al.  Towards an open question answering architecture , 2014, SEM '14.

[25]  Paul T. Groth,et al.  The Semantic Web – ISWC 2014 , 2014, Lecture Notes in Computer Science.

[26]  Lora Aroyo,et al.  The Semantic Web – ISWC 2013 , 2013, Lecture Notes in Computer Science.

[27]  Huajun Chen,et al.  The Semantic Web , 2011, Lecture Notes in Computer Science.

[28]  Enrico Motta,et al.  Is Question Answering fit for the Semantic Web?: A survey , 2011, Semantic Web.

[29]  Claudio Carpineto,et al.  A Survey of Automatic Query Expansion in Information Retrieval , 2012, CSUR.

[30]  Dongyan Zhao,et al.  Answering Natural Language Questions via Phrasal Semantic Parsing , 2014, CLEF.

[31]  Aditya Kalyanpur,et al.  Leveraging Community-Built Knowledge for Type Coercion in Question Answering , 2011, International Semantic Web Conference.

[32]  Fabio Ciravegna,et al.  Improving Semantic Search Using Query Log Analysis , 2012, ILD@ESWC.

[33]  Klaus U. Schulz,et al.  Fast string correction with Levenshtein automata , 2002, International Journal on Document Analysis and Recognition.

[34]  Irene Pimenta Rodrigues,et al.  Cooperative Question Answering for the Semantic Web , 2018, KMIS.

[35]  Gosse Bouma,et al.  Natural Language Processing and Information Systems , 2017, Lecture Notes in Computer Science.

[36]  Paul Buitelaar,et al.  Cross-Lingual Natural Language Querying over the Web of Data , 2013, NLDB.

[37]  Peter Kulchyski.  and , 2015 .

[38]  Roi Blanco,et al.  Federated Entity Search Using On-the-Fly Consolidation , 2013, International Semantic Web Conference.

[39]  Jens Lehmann,et al.  Towards question answering on statistical linked data , 2014, SEM '14.

[40]  Stephen Wolfram,et al.  The Mathematica Book , 1996 .

[41]  Philipp Cimiano,et al.  Flexible semantic composition with DUDES , 2009 .

[42]  Patrick Saint-Dizier,et al.  The KOMODO System: getting Recommendations on how to realize an action via Question-Answering , 2011 .

[43]  Dongyan Zhao,et al.  Natural language question answering over RDF: a graph data driven approach , 2014, SIGMOD Conference.

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

[45]  André Freitas,et al.  EasyESA: A Low-effort Infrastructure for Explicit Semantic Analysis , 2014, SEMWEB.

[46]  Seonyeong Park,et al.  ISOFT at QALD-4: Semantic Similarity-based Question Answering System over Linked Data , 2014, CLEF.

[47]  Maybin K. Muyeba,et al.  A Hybrid Approach using Ontology Similarity and Fuzzy Logic for Semantic Question Answering , 2017, ArXiv.

[48]  Fleur Mougin,et al.  Description of the POMELO System for the Task 2 of QALD-2014 , 2014, CLEF.

[49]  Aditya Kalyanpur,et al.  A Comparison of Hard Filters and Soft Evidence for Answer Typing in Watson , 2012, International Semantic Web Conference.

[50]  Seán O'Riain,et al.  Querying Linked Data Using Semantic Relatedness: A Vocabulary Independent Approach , 2011, NLDB.

[51]  Sören Auer,et al.  AGDISTIS - Graph-Based Disambiguation of Named Entities Using Linked Data , 2014, International Semantic Web Conference.

[52]  Lei Zou,et al.  Natural language question answering over RDF data , 2013, SIGMOD '13.

[53]  Gerhard Weikum,et al.  Robust question answering over the web of linked data , 2013, CIKM.

[54]  Erdogan Dogdu,et al.  Semantic question answering system over linked data using relational patterns , 2013, EDBT '13.

[55]  Rehab F. Abdel-Kader,et al.  QASYO: A Question Answering System for YAGO Ontology , 2011 .

[56]  Yelong Shen,et al.  Sparse hidden-dynamics conditional random fields for user intent understanding , 2011, WWW.

[57]  Axel-Cyrille Ngonga Ngomo,et al.  BioASQ: A Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering , 2012, AAAI Fall Symposium: Information Retrieval and Knowledge Discovery in Biomedical Text.

[58]  Oscar Corcho,et al.  The Semantic Web: Semantics and Big Data , 2013, Lecture Notes in Computer Science.

[59]  Interacting with Linked Data (ild 2012) , 2022 .

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

[61]  Corina Dima.  Answering Natural Language Questions with Intui3 , 2014, CLEF.

[62]  Gerhard Weikum,et al.  PATTY: A Taxonomy of Relational Patterns with Semantic Types , 2012, EMNLP.

[63]  Cui Tao,et al.  Time-Oriented Question Answering from Clinical Narratives Using Semantic-Web Techniques , 2010, SEMWEB.

[64]  Jens Lehmann,et al.  Keyword Query Expansion on Linked Data Using Linguistic and Semantic Features , 2013, 2013 IEEE Seventh International Conference on Semantic Computing.

[65]  Helmut Feldweg,et al.  GermaNet - a Lexical-Semantic Net for German , 1997 .

[66]  Fabio Ciravegna,et al.  NL-Graphs: A Hybrid Approach toward Interactively Querying Semantic Data , 2014, ESWC.

[67]  Ming-Wei Chang,et al.  Open Domain Question Answering via Semantic Enrichment , 2015, WWW.

[68]  Oren Etzioni,et al.  Paraphrase-Driven Learning for Open Question Answering , 2013, ACL.

[69]  Axel-Cyrille Ngonga Ngomo,et al.  Link Discovery with Guaranteed Reduction Ratio in Affine Spaces with Minkowski Measures , 2012, SEMWEB.

[70]  Shiyan Ou,et al.  An Entailment-Based Question Answering System over Semantic Web Data , 2011, ICADL.

[71]  Elena Cabrio,et al.  QALD-3: Multilingual Question Answering over Linked Data , 2013, CLEF.

[72]  Alia I. Abdelmoty,et al.  Hybrid Geo-spatial Query Methods on the Semantic Web with a Spatially-Enhanced Index of DBpedia , 2012, GIScience.

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

[74]  Sebastian Hellmann,et al.  Generating SPARQL queries using templates , 2013, Web Intell. Agent Syst..

[75]  Tim Furche,et al.  OXPath: A language for scalable data extraction, automation, and crawling on the deep web , 2012, The VLDB Journal.

[76]  Andrei Popescu-Belis,et al.  8th International Conference on Applications of Natural Language to Information Systems , 2003 .

[77]  Fabien L. Gandon,et al.  Querying Multilingual DBpedia with QAKiS , 2013, ESWC.

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

[79]  Gerhard Weikum,et al.  Natural Language Questions for the Web of Data , 2012, EMNLP.

[80]  Philipp Cimiano,et al.  Representing and resolving ambiguities in ontology-based question answering , 2011, TextInfer@EMNLP.

[81]  Yun Peng,et al.  Swoogle: Searching for Knowledge on the Semantic Web , 2005, AAAI.

[82]  Philipp Cimiano,et al.  Natural Language Interfaces: What Is the Problem? - A Data-Driven Quantitative Analysis , 2009, NLDB.

[83]  Marta Sabou,et al.  The Semantic Web. Latest Advances and New Domains , 2015, Lecture Notes in Computer Science.

[84]  Jeff Heflin,et al.  The Semantic Web – ISWC 2012 , 2012, Lecture Notes in Computer Science.

[85]  Lynette Hirschman,et al.  Natural language question answering: the view from here , 2001, Natural Language Engineering.

[86]  Sébastien Ferré,et al.  SQUALL: A Controlled Natural Language as Expressive as SPARQL 1.1 , 2013, NLDB.

[87]  Aarne Ranta,et al.  Grammatical Framework , 2004, Journal of Functional Programming.

[88]  Tim Kraska,et al.  CrowdQ: Crowdsourced Query Understanding , 2013, CIDR.

[89]  Wessel Kraaij,et al.  Working Notes for CLEF 2014 Conference, Sheffield, UK, September 15-18, 2014 , 2014, CLEF.

[90]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[91]  Working Notes for CLEF 2013 Conference , Valencia, Spain, September 23-26, 2013 , 2014, CLEF.

[92]  Jun Zhao,et al.  CASIA@V2: A MLN-based Question Answering System over Linked Data , 2014, CLEF.

[93]  Corina Dima.  Intui2: A Prototype System for Question Answering over Linked Data , 2013, CLEF.

[94]  Philipp Cimiano,et al.  Evaluation of a Layered Approach to Question Answering over Linked Data , 2012, International Semantic Web Conference.

[95]  Ryutaro Ichise,et al.  An Automated Template Selection Framework for Keyword Query over Linked Data , 2012, JIST.

[96]  Rodolfo Delmonte,et al.  From Logical Forms to SPARQL Query with GETARUN , 2011, DART@AI*IA.

[97]  Roberto Basili,et al.  A HMM-based Approach to Question Answering against Linked Data , 2013, CLEF.

[98]  Axel-Cyrille Ngonga Ngomo,et al.  HAWK - Hybrid Question Answering over Linked Data , 2015, ESWC 2015.

[99]  Aditya Kalyanpur,et al.  Predicting Lexical Answer Types in Open Domain QA , 2012, Int. J. Semantic Web Inf. Syst..

[100]  André Freitas,et al.  Natural language queries over heterogeneous linked data graphs: a distributional-compositional semantics approach , 2014, IUI.

[101]  André Freitas,et al.  Treo: Combining Entity-Search, Spreading Activation and Semantic Relatedness for Querying Linked Data , 2011 .

[102]  Sébastien Ferré.  squall2sparql: a Translator from Controlled English to Full SPARQL 1.1 , 2013, CLEF.

[103]  Sören Auer,et al.  Question answering on interlinked data , 2013, WWW.

[104]  Jun Zhao,et al.  CASIA@QALD-3: A Question Answering System over Linked Data , 2013, CLEF.

[105]  Amit P. Sheth,et al.  Alignment-Based Querying of Linked Open Data , 2012, OTM Conferences.

[106]  Richard A. Frost,et al.  A Demonstration of a Natural Language Query Interface to an Event-Based Semantic Web Triplestore , 2014, ESWC.

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

[108]  Lora Aroyo,et al.  The Semantic Web: Research and Applications , 2009, Lecture Notes in Computer Science.

[109]  Seán O'Riain,et al.  Querying Heterogeneous Datasets on the Linked Data Web: Challenges, Approaches, and Trends , 2012, IEEE Internet Computing.

[110]  Gerhard Weikum,et al.  YAGO-QA: Answering Questions by Structured Knowledge Queries , 2011, 2011 IEEE Fifth International Conference on Semantic Computing.

[111]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[112]  Jens Lehmann,et al.  Template-based question answering over RDF data , 2012, WWW.

[113]  Axel-Cyrille Ngonga Ngomo,et al.  Extracting Multilingual Natural-Language Patterns for RDF Predicates , 2012, EKAW.

[114]  Philipp Cimiano,et al.  Pythia: Compositional Meaning Construction for Ontology-Based Question Answering on the Semantic Web , 2011, NLDB.

[115]  Roi Blanco,et al.  Effective and Efficient Entity Search in RDF Data , 2011, SEMWEB.

[116]  Hyoil Han,et al.  Biomedical question answering: A survey , 2010, Comput. Methods Programs Biomed..

[117]  Ning Zhong,et al.  SEMANTIC MAPPING FROM NATURAL LANGUAGE QUESTIONS TO OWL QUERIES , 2011, Comput. Intell..

[118]  Fabien L. Gandon,et al.  Filling the gaps among DBpedia multilingual chapters for question answering , 2013, WebSci.

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