Automatic stop list generation for clustering recognition results of call center recordings

Standard

Automatic stop list generation for clustering recognition results of call center recordings. / Popova, S.; Krivosheeva, T.; Korenevsky, M.

In: Lecture Notes in Computer Science, Vol. 8773, 2014, p. 137-144.

Research output: Contribution to journal › Article

Author

Popova, S. ; Krivosheeva, T. ; Korenevsky, M. / Automatic stop list generation for clustering recognition results of call center recordings. In: Lecture Notes in Computer Science. 2014 ; Vol. 8773. pp. 137-144.

BibTeX

@article{80b80e90c5f64c52a1b40321c9b38c46,

title = "Automatic stop list generation for clustering recognition results of call center recordings",

abstract = "The paper deals with the problem of automatic stop list generation for processing recognition results of call center recordings, in particular for the purpose of clustering. We propose and test a supervised domain dependent method of automatic stop list generation. The method is based on finding words whose removal increases the dissimilarity between documents in different clusters, and decreases dissimilarity between documents within the same cluster. This approach is shown to be efficient for clustering recognition results of recordings with different quality, both on datasets that contain the same topics as the training dataset, and on datasets containing other topics.",

keywords = "ASR, Clustering, Stop list generation, Stop Words",

author = "S. Popova and T. Krivosheeva and M. Korenevsky",

year = "2014",

language = "не определен",

volume = "8773",

pages = "137--144",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Nature",

}

RIS

TY - JOUR

T1 - Automatic stop list generation for clustering recognition results of call center recordings

AU - Popova, S.

AU - Krivosheeva, T.

AU - Korenevsky, M.

PY - 2014

Y1 - 2014

N2 - The paper deals with the problem of automatic stop list generation for processing recognition results of call center recordings, in particular for the purpose of clustering. We propose and test a supervised domain dependent method of automatic stop list generation. The method is based on finding words whose removal increases the dissimilarity between documents in different clusters, and decreases dissimilarity between documents within the same cluster. This approach is shown to be efficient for clustering recognition results of recordings with different quality, both on datasets that contain the same topics as the training dataset, and on datasets containing other topics.

AB - The paper deals with the problem of automatic stop list generation for processing recognition results of call center recordings, in particular for the purpose of clustering. We propose and test a supervised domain dependent method of automatic stop list generation. The method is based on finding words whose removal increases the dissimilarity between documents in different clusters, and decreases dissimilarity between documents within the same cluster. This approach is shown to be efficient for clustering recognition results of recordings with different quality, both on datasets that contain the same topics as the training dataset, and on datasets containing other topics.

KW - ASR

KW - Clustering

KW - Stop list generation

KW - Stop Words

M3 - статья

VL - 8773

SP - 137

EP - 144

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -

ID: 5746798