Stage-oe-small.jpg

Inproceedings3267: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Ell |ErsterAutorVorname=Basil }} {{Publikation Author |Rank=2 |Author=Denny Vrandecic }} {{Publikation Author |Ran…“)
 
 
(5 dazwischenliegende Versionen von 2 Benutzern werden nicht angezeigt)
Zeile 12: Zeile 12:
 
}}
 
}}
 
{{Inproceedings
 
{{Inproceedings
|Referiert=False
+
|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

BibTeX


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

Projekt

Render


Verknüpfte Tools

Spartiqulation


Forschungsgruppe

Wissensmanagement


Forschungsgebiet