Stage-oe-small.jpg

Inproceedings3564: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
Zeile 26: Zeile 26:
 
|Abstract=A lot of current web pages include structured data which can di- rectly be processed and used. Search engines, in particular, gather that structured data and provide question answering capabilities over the integrated data with an entity-centric presentation of the results. Due to the decentralized nature of the web, multiple struc- tured data sources can provide similar information about an entity. But data from di erent sources may involve di erent vocabular- ies and modeling granularities, which makes integration di cult. We present an approach that identi es similar entity-speci c data across sources, independent of the vocabulary and data modeling choices. We apply our method along the scenario of a trustable knowledge panel, conduct experiments in which we identify and process entity data from web sources, and compare the output to a competing system. The results underline the advantages of the presented entity-centric data fusion approach.
 
|Abstract=A lot of current web pages include structured data which can di- rectly be processed and used. Search engines, in particular, gather that structured data and provide question answering capabilities over the integrated data with an entity-centric presentation of the results. Due to the decentralized nature of the web, multiple struc- tured data sources can provide similar information about an entity. But data from di erent sources may involve di erent vocabular- ies and modeling granularities, which makes integration di cult. We present an approach that identi es similar entity-speci c data across sources, independent of the vocabulary and data modeling choices. We apply our method along the scenario of a trustable knowledge panel, conduct experiments in which we identify and process entity data from web sources, and compare the output to a competing system. The results underline the advantages of the presented entity-centric data fusion approach.
 
|Download=Entity-centric Data Fusion on the Web.pdf,
 
|Download=Entity-centric Data Fusion on the Web.pdf,
|DOI Name=https://doi.org/10.1145/3078714.3078717
+
|DOI Name=10.1145/3078714.3078717
 
|Projekt=SemData, SumOn
 
|Projekt=SemData, SumOn
 
|Forschungsgruppe=Web Science
 
|Forschungsgruppe=Web Science
 
}}
 
}}

Version vom 21. Juli 2017, 15:24 Uhr


Entity-centric Data Fusion on the Web


Entity-centric Data Fusion on the Web



Published: 2017 Juli

Buchtitel: Proceedings of the 28th ACM Conference on Hypertext and Social Media
Verlag: ACM

Referierte Veröffentlichung

BibTeX

Kurzfassung
A lot of current web pages include structured data which can di- rectly be processed and used. Search engines, in particular, gather that structured data and provide question answering capabilities over the integrated data with an entity-centric presentation of the results. Due to the decentralized nature of the web, multiple struc- tured data sources can provide similar information about an entity. But data from di erent sources may involve di erent vocabular- ies and modeling granularities, which makes integration di cult. We present an approach that identi es similar entity-speci c data across sources, independent of the vocabulary and data modeling choices. We apply our method along the scenario of a trustable knowledge panel, conduct experiments in which we identify and process entity data from web sources, and compare the output to a competing system. The results underline the advantages of the presented entity-centric data fusion approach.

Download: Media:Entity-centric Data Fusion on the Web.pdf
DOI Link: 10.1145/3078714.3078717

Projekt

SemDataSumOn



Forschungsgruppe

Web Science


Forschungsgebiet