Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.2498/cit.1002190

Domain-aware Evaluation of Named Entity Recognition Systems for Croatian

Zeljko Agic ; University of Zagreb
Bozo Bekavac ; Department of Linguistics, Faculty of Humanities and Social Sciences, University of Zagreb


Puni tekst: engleski pdf 439 Kb

str. 195-209

preuzimanja: 691

citiraj


Sažetak

We provide an evaluation of the currently available named entity recognition systems for Croatian. The evaluation puts special emphasis on domain dependence. To this goal, we manually annotated a dataset of approximately 1 million tokens of Croatian text from various domains within the newspaper text genre. The dataset was annotated using a three-class named entity tagset – denoting personal names, locations and organizations. We give insight to feature selection, domain sensitivity and effects of increase in training set size for statistical named entity recognition using the state-of-the-art Stanford NER system. We also sketch a comparison of publicly available named entity recognition systems for Croatian considering domain dependence, regardless of their underlying paradigms. Our top-performing system achieved an F1-score of 0.884 in a mixed-domain testing scenario, scoring 0.925 and 0.843 in the two domains separated for the experiment. The system shows consistency in state-of-the-art scores for detecting names of persons, locations and organizations.

Ključne riječi

named entity recognition; Croatian language; text domain; domain dependence; evaluation

Hrčak ID:

110027

URI

https://hrcak.srce.hr/110027

Datum izdavanja:

31.10.2013.

Posjeta: 1.330 *