Přejít na obsah

Detail publikace


Lucie Skorkovská and Zbyněk Zajíc : Score Normalization Methods Applied to Topic Identification . Text, Speech, and Dialogue, 17th International Conference, TSD 2014, Lecture Notes in Artificial Intelligence, vol. 8655, p. 133-140, Springer, 2014.

PDF ke stažení



Multi-label classification plays the key role in modern categorization systems. Its goal is to find a set of labels belonging to each data item. In the multi-label document classification unlike in the multi-class classification, where only the best topic is chosen, the classifier must decide if a document does or does not belong to each topic from the predefined topic set. We are using the generative classifier to tackle this task, but the problem with this approach is that the threshold for the positive classification must be set. This threshold can vary for each document depending on the content of the document (words used, length of the document, ...). In this paper we use the Unconstrained Cohort Normalization, primary proposed for speaker identification/verification task, for robustly finding the threshold defining the boundary between the correct and the incorrect topics of a document. In our former experiments we have proposed a method for finding this threshold inspired by another normalization technique called World Model score normalization. Comparison of these normalization methods has shown that better results can be achieved from the Unconstrained Cohort Normalization.

Detail publikace

Název: Score Normalization Methods Applied to Topic Identification
Autor: Lucie Skorkovská ; Zbyněk Zajíc
Název - česky: Metody normalizace skóre použité pro identifikaci tématu
Jazyk publikace: anglicky
Rok vydání: 2014
Typ publikace: Stať ve sborníku
Název časopisu / knihy: Text, Speech, and Dialogue, 17th International Conference, TSD 2014
Svazek: Lecture Notes in Artificial Intelligence
Číslo vydání: 8655
Strana: 133 - 140
DOI: 10.1007/978-3-319-10816-2_17
ISBN: 978-3-319-10815-5
ISSN: 0302-9743
Nakladatel: Springer
Datum: 8.9.2014 - 12.9.2014
/ 2014-11-13 10:36:00 /

Klíčová slova

topic identification, multi-label text classification, Naive Bayes classification, score normalization

Klíčová slova v češtině

identifikace tématu, klasifikace textu do více témat, Bayesovská klasifikace, normalizace skóre


 author = {Lucie Skorkovsk\'{a} and Zbyn\v{e}k Zaj\'{i}c},
 title = {Score Normalization Methods Applied to Topic Identification},
 year = {2014},
 publisher = {Springer},
 journal = {Text, Speech, and Dialogue, 17th International Conference, TSD 2014},
 volume = {8655},
 pages = {133-140},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-319-10815-5},
 ISSN = {0302-9743},
 doi = {10.1007/978-3-319-10816-2_17},
 url = {http://www.kky.zcu.cz/en/publications/LucieSkorkovska_2014_ScoreNormalization},