Stage-oe-small.jpg

Inproceedings3429: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
Zeile 25: Zeile 25:
 
|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.
  
(This is an extended version of the [[Inproceedings3267|ESWC 2012 ILD paper]])
+
(This is an extended version of the [[Inproceedings3267 ESWC 2012 ILD paper]])
 
|Download=ESWC2012-PP SPARQL.pdf,
 
|Download=ESWC2012-PP SPARQL.pdf,
 
|Projekt=Render
 
|Projekt=Render
 
|Forschungsgruppe=Wissensmanagement
 
|Forschungsgruppe=Wissensmanagement
 
}}
 
}}

Version vom 5. August 2014, 10:52 Uhr


SPARTIQULATION: Verbalizing SPARQL queries


SPARTIQULATION: Verbalizing SPARQL queries



Published: 2012 Mai

Buchtitel: Proceedings of the 11th Extended Semantic Web Conference,
Verlag: Springer

Referierte Veröffentlichung

BibTeX


Kurzfassung
[[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.

(This is an extended version of the Inproceedings3267 ESWC 2012 ILD paper)]]

Download: Media:ESWC2012-PP SPARQL.pdf

Projekt

Render


Verknüpfte Tools

Spartiqulation


Forschungsgruppe

Wissensmanagement


Forschungsgebiet