Přejít na obsah

Detail publikace

Citace

Lucie Skorkovská : First Experiments with Relevant Documents Selection for Blind Relevance Feedback in Spoken Document Retrieval . Speech and Computer, 16th International Conference, SPECOM 2014, Lecture Notes in Artificial Intelligence, vol. 8773, p. 235-242, Springer, Heidelberg, 2014.

PDF ke stažení

PDF

Abstrakt

This paper presents our first experiments aimed at the automatic selection of the relevant documents for the blind relevance feedback method in speech information retrieval. Usually the relevant documents are selected only by simply determining the first N documents to be relevant. We consider this approach to be insufficient and we would try in this paper to outline the possibilities of the dynamical selection of the relevant documents for each query depending on the content of the retrieved documents instead of just blindly defining the number of the relevant documents to be used for the blind relevance feedback in advance. We have performed initial experiments with the application of the score normalization techniques used in the speaker identification task, which was successfully used in the multi-label classification task for finding the “correct” topics of a newspaper article in the output of a generative classifier. The experiments have shown promising results, therefore they will be used to define the possibilities of the subsequent research in this area.

Detail publikace

Název: First Experiments with Relevant Documents Selection for Blind Relevance Feedback in Spoken Document Retrieval
Autor: Lucie Skorkovská
Název - česky: První experimenty se selekcí relevantních dokumentů pro zpětnou vazbu ve vyhledávání informací v řeči
Jazyk publikace: anglicky
Rok vydání: 2014
Typ publikace: Stať ve sborníku
Název časopisu / knihy: Speech and Computer, 16th International Conference, SPECOM 2014
Svazek: Lecture Notes in Artificial Intelligence
Číslo vydání: 8773
Strana: 235 - 242
DOI: 10.1007/978-3-319-11581-8_29
ISBN: 978-3-319-11580-1
ISSN: 0302-9743
Nakladatel: Springer
Místo vydání: Heidelberg
Datum: 5.10.2014 - 9.10.2014
/ 2014-11-13 10:42:45 /

Klíčová slova

query expansion, blind relevance feedback, spoken document retrieval, score normalization

Klíčová slova v češtině

rozšíření dotazu, automatická zpětná vazba, vyhledávání informací v řeči, normalizace skóre

BibTeX

@INPROCEEDINGS{LucieSkorkovska_2014_FirstExperiments,
 author = {Lucie Skorkovsk\'{a}},
 title = {First Experiments with Relevant Documents Selection for Blind Relevance Feedback in Spoken Document Retrieval},
 year = {2014},
 publisher = {Springer},
 journal = {Speech and Computer, 16th International Conference, SPECOM 2014},
 address = {Heidelberg},
 volume = {8773},
 pages = {235-242},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-319-11580-1},
 ISSN = {0302-9743},
 doi = {10.1007/978-3-319-11581-8_29},
 url = {http://www.kky.zcu.cz/en/publications/LucieSkorkovska_2014_FirstExperiments},
}