New Workshop Paper: Corrupting Evaluation Datasets

This paper combines the work of my PhD student Ahmad Alsadeeqi on corrupting data sets with my colleague Fiona McNeill’s work on ontology matching for disaster response.

1. Generating corrupted data sources for the evaluation of matching systems

   Abstract: One of the most difficult aspects of developing matching systems – whether for matching ontologies or for other types of mismatched data – is evaluation. The accuracy of matchers are usually evaluated by measuring the results produced by the systems against reference sets, but gold-standard reference sets are expensive and difficult to create. In this paper we introduce crptr, which generates multiple variations of different sorts of dataset, where the degree of variation is controlled, in order that they can be used to evaluate matchers in different context.

   McNeill, Fiona and Bental, Diana and Gray, Alasdair J. G. and Jedrzejczyk, Sabina and Alsadeeqi, Ahmad

   In The Fourteenth International Workshop on Ontology Matching, CEUR Workshop Proceedings, 2536, pages 41–45, CEUR Workshop Proceedings (CEUR-WS.org), 2019

   @inproceedings{McNeill:crptr-matching-evaluation:OM2019,
     title = {Generating corrupted data sources for the evaluation of matching systems},
     keywords = {Matching, Evaluation, Data Corruption},
     author = {McNeill, Fiona and Bental, Diana and Gray, Alasdair J. G. and Jedrzejczyk, Sabina and Alsadeeqi, Ahmad},
     year = {2019},
     month = oct,
     series = {CEUR Workshop Proceedings},
     publisher = {CEUR Workshop Proceedings (CEUR-WS.org)},
     volume = {2536},
     pages = {41--45},
     booktitle = {The Fourteenth International Workshop on Ontology Matching},
     url = {http://ceur-ws.org/Vol-2536/om2019_STpaper2.pdf}
   }
   

About Me

I'm an Associate Professor in Computer Science at Heriot-Watt University. My research focuses on linking datasets. Read more

Tweets

Tweets by gray_alasdair