@inproceedings{3670463c1b124476af9e8bf3768b9d08,
title = "Classification of historical notary acts with noisy labels",
abstract = "This paper approaches the problem of automatic classification of real-world historical notary acts from the 14th to the 20th century. We deal with category ambiguity, noisy labels and imbalanced data. Our goal is to assign an appropriate category for each notary act from the archive collection. We investigate a variety of existing techniques and describe a framework for dealing with noisy labels which includes category resolution, evaluation of inter-annotator agreement and the application of a two level classification. The maximum accuracy we achieve is 88%, which is comparable to the agreement between human annotators.",
author = "I. Efremova and {Montes Garcia}, A. and T.G.K. Calders",
year = "2015",
doi = "10.1007/978-3-319-16354-3_6",
language = "English",
isbn = "978-3-319-16353-6",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "49--54",
editor = "A. Hanbury and G. Kazai and A. Rauber and N. Fuhr",
booktitle = "Advances in Information Retrieval (37th European Conference on IR Research, ECIR 2015, Vienna, Austria, March 29-April 2, 2015. Proceedings)",
address = "Germany",
note = "37th European Conference on Information Retrieval (ECIR 2015), March 29-April 2, 2015, Vienna, Austria, ECIR 2015 ; Conference date: 29-03-2015 Through 02-04-2015",
}