{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:32:17Z","timestamp":1784298737323,"version":"3.55.0"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2016,8]]},"abstract":"<jats:p>In this paper, we present ATHENA, an ontology-driven system for natural language querying of complex relational databases. Natural language interfaces to databases enable users easy access to data, without the need to learn a complex query language, such as SQL. ATHENA uses domain specific ontologies, which describe the semantic entities, and their relationships in a domain. We propose a unique two-stage approach, where the input natural language query (NLQ) is first translated into an intermediate query language over the ontology, called OQL, and subsequently translated into SQL. Our two-stage approach allows us to decouple the physical layout of the data in the relational store from the semantics of the query, providing physical independence. Moreover, ontologies provide richer semantic information, such as inheritance and membership relations, that are lost in a relational schema. By reasoning over the ontologies, our NLQ engine is able to accurately capture the user intent. We study the effectiveness of our approach using three different workloads on top of geographical (GEO), academic (MAS) and financial (FIN) data. ATHENA achieves 100% precision on the GEO and MAS workloads, and 99% precision on the FIN workload which operates on a complex financial ontology. Moreover, ATHENA attains 87.2%, 88.3%, and 88.9% recall on the GEO, MAS, and FIN workloads, respectively.<\/jats:p>","DOI":"10.14778\/2994509.2994536","type":"journal-article","created":{"date-parts":[[2016,9,6]],"date-time":"2016-09-06T15:27:03Z","timestamp":1473175623000},"page":"1209-1220","source":"Crossref","is-referenced-by-count":126,"title":["ATHENA"],"prefix":"10.14778","volume":"9","author":[{"given":"Diptikalyan","family":"Saha","sequence":"first","affiliation":[{"name":"IBM Research. Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avrilia","family":"Floratou","sequence":"additional","affiliation":[{"name":"IBM Research. Almaden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karthik","family":"Sankaranarayanan","sequence":"additional","affiliation":[{"name":"IBM Research. Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umar Farooq","family":"Minhas","sequence":"additional","affiliation":[{"name":"IBM Research. Almaden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish R.","family":"Mittal","sequence":"additional","affiliation":[{"name":"IBM Research. Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatma","family":"\u00d6zcan","sequence":"additional","affiliation":[{"name":"IBM Research. Almaden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2016,8]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Weakly Connected Directed Graph. http:\/\/mathworld.wolfram.com\/WeaklyConnectedDigraph.html.  Weakly Connected Directed Graph. http:\/\/mathworld.wolfram.com\/WeaklyConnectedDigraph.html."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/876875.879013"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1017\/S135132490000005X"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2735361"},{"key":"e_1_2_1_5_1","first-page":"1533","volume-title":"EMNLP","author":"Berant J.","year":"2013","unstructured":"J. Berant Semantic Parsing on Freebase from Question-Answer Pairs . In EMNLP , pages 1533 -- 1544 , 2013 . J. Berant et al. Semantic Parsing on Freebase from Question-Answer Pairs. In EMNLP, pages 1533--1544, 2013."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536274.2536281"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/876875.879034"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336667"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12550-8_16"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04957-6_37"},{"key":"e_1_2_1_11_1","unstructured":"Stanford Dependency Parser. http:\/\/stanfordnlp.github.io\/CoreNLP\/depparse.html.  Stanford Dependency Parser. http:\/\/stanfordnlp.github.io\/CoreNLP\/depparse.html."},{"key":"e_1_2_1_12_1","volume-title":"WordNet Interface","author":"Feinerer I.","year":"2016","unstructured":"I. Feinerer and K. Hornik . WordNet Interface , 2016 . I. Feinerer and K. Hornik. WordNet Interface, 2016."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920932"},{"key":"e_1_2_1_14_1","volume-title":"VLDB","author":"Hristidis V.","year":"2002","unstructured":"V. Hristidis and Y. Papakonstantinou . Discover: Keyword Search in Relational Databases . In VLDB , 2002 . V. Hristidis and Y. Papakonstantinou. Discover: Keyword Search in Relational Databases. In VLDB, 2002."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00288961"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/170035.171543"},{"key":"e_1_2_1_17_1","volume-title":"LREC","author":"Lafourcade M.","year":"2002","unstructured":"M. Lafourcade and C. Boitet . UNL Lexical Selection with Conceptual Vectors . In LREC , 2002 . M. Lafourcade and C. Boitet. UNL Lexical Selection with Conceptual Vectors. In LREC, 2002."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSDM.1997.621175"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735461.2735468"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066281"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/980691.980696"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/7239.384276"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_2_1_24_1","first-page":"608","volume-title":"Answering Controlled Natural Language Questions on RDF Knowledge Bases. In EDBT 2016","author":"Mazzeo G. M.","year":"2016","unstructured":"G. M. Mazzeo and C. Zaniolo . Answering Controlled Natural Language Questions on RDF Knowledge Bases. In EDBT 2016 , pages 608 -- 611 , 2016 . G. M. Mazzeo and C. Zaniolo. Answering Controlled Natural Language Questions on RDF Knowledge Bases. In EDBT 2016, pages 608--611, 2016."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2012.07.001"},{"key":"e_1_2_1_27_1","volume-title":"VLDB","author":"Pedersen T. B.","year":"1999","unstructured":"T. B. Pedersen Extending Practical Pre-Aggregation in On-Line Analytical Processing . In VLDB , 1999 . T. B. Pedersen et al. Extending Practical Pre-Aggregation in On-Line Analytical Processing. In VLDB, 1999."},{"issue":"2","key":"e_1_2_1_28_1","first-page":"155","article-title":"A bound for the steiner tree problem in graphs","volume":"31","author":"Plesn\u00edk J.","year":"1981","unstructured":"J. Plesn\u00edk . A bound for the steiner tree problem in graphs . Mathematica Slovaca , 31 ( 2 ): 155 -- 163 , 1981 . J. Plesn\u00edk. A bound for the steiner tree problem in graphs. Mathematica Slovaca, 31(2):155--163, 1981.","journal-title":"Mathematica Slovaca"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220376"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/604045.604070"},{"issue":"2","key":"e_1_2_1_31_1","first-page":"297","article-title":"A Comprehensive Study on Natural Language Processing and Natural Language Interface to Databases","volume":"9","author":"Shafique U.","year":"2014","unstructured":"U. Shafique and H. Qaiser . A Comprehensive Study on Natural Language Processing and Natural Language Interface to Databases . International Journal of Innovation and Scientific Research , 9 ( 2 ): 297 -- 306 , 2014 . U. Shafique and H. Qaiser. A Comprehensive Study on Natural Language Processing and Natural Language Interface to Databases. International Journal of Innovation and Scientific Research, 9(2):297--306, 2014.","journal-title":"International Journal of Innovation and Scientific Research"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-007-0075-9"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44795-4_40"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376705"},{"key":"e_1_2_1_35_1","unstructured":"TIMEX Annotator. http:\/\/ilps.science.uva.nl\/resources\/timextag\/.  TIMEX Annotator. http:\/\/ilps.science.uva.nl\/resources\/timextag\/."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/2994509.2994536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T10:54:49Z","timestamp":1672224889000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/2994509.2994536"}},"subtitle":["an ontology-driven system for natural language querying over relational data stores"],"short-title":[],"issued":{"date-parts":[[2016,8]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2016,8]]}},"alternative-id":["10.14778\/2994509.2994536"],"URL":"https:\/\/doi.org\/10.14778\/2994509.2994536","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2016,8]]}}}