Inproceedings3267: Unterschied zwischen den Versionen
Bel (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Ell |ErsterAutorVorname=Basil }} {{Publikation Author |Rank=2 |Author=Denny Vrandecic }} {{Publikation Author |Ran…“) |
Ph1272 (Diskussion | Beiträge) |
||
(5 dazwischenliegende Versionen von 2 Benutzern werden nicht angezeigt) | |||
Zeile 12: | Zeile 12: | ||
}} | }} | ||
{{Inproceedings | {{Inproceedings | ||
− | |Referiert= | + | |Referiert=True |
|Title=SPARTIQULATION: Verbalizing SPARQL queries | |Title=SPARTIQULATION: Verbalizing SPARQL queries | ||
|Year=2012 | |Year=2012 | ||
Zeile 18: | Zeile 18: | ||
|Booktitle=Proceedings of the International Workshop on Interacting with Linked Data (ILD 2012), Extended Semantic Web Conference (ESWC) | |Booktitle=Proceedings of the International Workshop on Interacting with Linked Data (ILD 2012), Extended Semantic Web Conference (ESWC) | ||
|Publisher=CEUR-WS.org | |Publisher=CEUR-WS.org | ||
+ | }} | ||
+ | {{Publikation Tool | ||
+ | |Tool=Spartiqulation | ||
}} | }} | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=Much research has been done to combine the fields of Databases and Natural Language Processing. While many works focus on the problem of deriving a structured query for a given natural language question, the problem of query verbalization - translating a structured query into natural language - is less explored. In this work we describe our approach to verbalizing SPARQL queries in order to create natural language expressions that are readable and understandable by the human day-to-day user. These expressions are helpful when having search engines generate SPARQL queries for user-provided natural language questions or keywords and enable the user to check whether the right question has been understood. While our approach enables verbalization of only a subset of SPARQL 1.1, this subset applies to 85% of the 209 queries in our training set. These observations are based on a corpus of SPARQL queries consisting of datasets from the QALD-1 challenge and the ILD2012 challenge. | |Abstract=Much research has been done to combine the fields of Databases and Natural Language Processing. While many works focus on the problem of deriving a structured query for a given natural language question, the problem of query verbalization - translating a structured query into natural language - is less explored. In this work we describe our approach to verbalizing SPARQL queries in order to create natural language expressions that are readable and understandable by the human day-to-day user. These expressions are helpful when having search engines generate SPARQL queries for user-provided natural language questions or keywords and enable the user to check whether the right question has been understood. While our approach enables verbalization of only a subset of SPARQL 1.1, this subset applies to 85% of the 209 queries in our training set. These observations are based on a corpus of SPARQL queries consisting of datasets from the QALD-1 challenge and the ILD2012 challenge. | ||
+ | |Download=ILD2012 SPARQL.pdf, | ||
|Projekt=Render | |Projekt=Render | ||
|Forschungsgruppe=Wissensmanagement | |Forschungsgruppe=Wissensmanagement | ||
}} | }} |
Aktuelle Version vom 5. August 2014, 09:58 Uhr
SPARTIQULATION: Verbalizing SPARQL queries
SPARTIQULATION: Verbalizing SPARQL queries
Published: 2012
Mai
Buchtitel: Proceedings of the International Workshop on Interacting with Linked Data (ILD 2012), Extended Semantic Web Conference (ESWC)
Verlag: CEUR-WS.org
Referierte Veröffentlichung
Kurzfassung
Much research has been done to combine the fields of Databases and Natural Language Processing. While many works focus on the problem of deriving a structured query for a given natural language question, the problem of query verbalization - translating a structured query into natural language - is less explored. In this work we describe our approach to verbalizing SPARQL queries in order to create natural language expressions that are readable and understandable by the human day-to-day user. These expressions are helpful when having search engines generate SPARQL queries for user-provided natural language questions or keywords and enable the user to check whether the right question has been understood. While our approach enables verbalization of only a subset of SPARQL 1.1, this subset applies to 85% of the 209 queries in our training set. These observations are based on a corpus of SPARQL queries consisting of datasets from the QALD-1 challenge and the ILD2012 challenge.
Download: Media:ILD2012 SPARQL.pdf