• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Evaluating Large-Scale Text Mining Applications Beyond the Traditional Numeric Performance Measures

Sofie van Landeghem, Suwisa Kaewphan, Filip Ginter, Yves van de Peer, Evaluating Large-Scale Text Mining Applications Beyond the Traditional Numeric Performance Measures. In: Claire Nédellec, Robert Bossy, Jin-Dong Kim, Jung-jae Kim, Tomoko Ohta, Sampo Pyysalo, Pierre Zweigenbaum (Eds.), Proceedings of the 2013 Workshop on Biomedical Natural Language Processing (BioNLP'13), 63–71, Association for Computational Linguistics (ACL), 2013.

Abstract:

Text mining methods for the biomedical
domain have matured substantially and
are currently being applied on a large
scale to support a variety of applications in systems biology, pathway curation, data integration and gene summarization. Community-wide challenges in the BioNLP research field provide gold-standard datasets and rigorous evaluation criteria, allowing for a meaningful comparison between techniques as well as measuring progress within the field. However, such evaluations are typically conducted on relatively small training and test datasets. On a larger scale, systematic erratic behaviour may occur that severely influences hundreds of thousands of predictions. In this work, we perform a critical assessment of a large-scale text mining resource, identifying systematic errors and etermining their underlying causes through semi-automated analyses and manual evaluations.

Files:

Full publication in PDF-format

BibTeX entry:

@INPROCEEDINGS{inpVaKaGiVa13a,
  title = {Evaluating Large-Scale Text Mining Applications Beyond the Traditional Numeric Performance Measures},
  booktitle = {Proceedings of the 2013 Workshop on Biomedical Natural Language Processing (BioNLP'13)},
  author = {Landeghem, Sofie van and Kaewphan, Suwisa and Ginter, Filip and Peer, Yves van de},
  editor = {Nédellec, Claire and Bossy, Robert and Kim, Jin-Dong and Kim, Jung-jae and Ohta, Tomoko and Pyysalo, Sampo and Zweigenbaum, Pierre},
  publisher = {Association for Computational Linguistics (ACL)},
  pages = {63–71},
  year = {2013},
}

Belongs to TUCS Research Unit(s): Turku BioNLP Group

Edit publication