@InProceedings{marinova-EtAl:2020:LREC,
  author    = {Marinova, Iva  and  Laskova, Laska  and  Osenova, Petya  and  Simov, Kiril  and  Popov, Alexander},
  title     = {Reconstructing NER Corpora: a Case Study on Bulgarian},
  booktitle      = {Proceedings of The 12th Language Resources and Evaluation Conference},
  month          = {May},
  year           = {2020},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {4647--4652},
  abstract  = {The paper reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus. We show how the annotations in a type-based corpus of named entities (NE) were populated as occurrences within it, thus ensuring density of the training information. A deep learning model was adopted for discovering inconsistencies in the initial annotation and for learning new NE types. The evaluation results get improved after data curation, randomization and deduplication.},
  url       = {https://www.aclweb.org/anthology/2020.lrec-1.571}
}