Modelirovanie i Analiz Informatsionnykh Sistem
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Impact factor

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Model. Anal. Inform. Sist.:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Modelirovanie i Analiz Informatsionnykh Sistem, 2021, Volume 28, Number 3, Pages 292–311
DOI: https://doi.org/10.18255/1818-1015-2021-3-292-311
(Mi mais751)
 

This article is cited in 1 scientific paper (total in 1 paper)

Theory of data

Word-embedding based text vectorization using clustering

V. I. Yufereva, N. A. Razinb

a Department of Information Technologies of the Central Bank of the Russian Federation, Laboratory of innovations ”Novosibirsk”, 12 Neglinnaya str., Moscow 107016, Russia
b Department of Counteraction to Unfair Practices, the Central Bank of the Russian Federation, 12 Neglinnaya str., Moscow 107016, Russia
Full-text PDF (814 kB) Citations (1)
References:
Abstract: It is known that in the tasks of natural language processing, the representation of texts by vectors of fixed length using word-embedding models makes sense in cases where the vectorized texts are short.
The longer the texts being compared, the worse the approach works. This situation is due to the fact that when using word-embedding models, information is lost when converting the vector representations of the words that make up the text into a vector representation of the entire text, which usually has the same dimension as the vector of a single word.
This paper proposes an alternative way for using pre-trained word-embedding models for text vectorization. The essence of the proposed method consists in combining semantically similar elements of the dictionary of the existing text corpus by clustering their (dictionary elements) embeddings, as a result of which a new dictionary is formed with a size smaller than the original one, each element of which corresponds to one cluster. The original corpus of texts is reformulated in terms of this new dictionary, after which vectorization is performed on the reformulated texts using one of the dictionary approaches (TF-IDF was used in the work). The resulting vector representation of the text can be additionally enriched using the vectors of words of the original dictionary obtained by decreasing the dimension of their embeddings for each cluster.
A series of experiments to determine the optimal parameters of the method is described in the paper, the proposed approach is compared with other methods of text vectorization for the text ranking problem — averaging word embeddings with TF-IDF weighting and without weighting, as well as vectorization based on TF-IDF coefficients.
Keywords: word embedding, Fasttext, TF-IDF, averaging, clustering, text similarity, distance, text ranking.
Received: 23.06.2021
Revised: 16.08.2021
Accepted: 25.08.2021
Document Type: Article
UDC: 004.8
MSC: 97R40, 68T50
Language: Russian
Citation: V. I. Yuferev, N. A. Razin, “Word-embedding based text vectorization using clustering”, Model. Anal. Inform. Sist., 28:3 (2021), 292–311
Citation in format AMSBIB
\Bibitem{YufRaz21}
\by V.~I.~Yuferev, N.~A.~Razin
\paper Word-embedding based text vectorization using clustering
\jour Model. Anal. Inform. Sist.
\yr 2021
\vol 28
\issue 3
\pages 292--311
\mathnet{http://mi.mathnet.ru/mais751}
\crossref{https://doi.org/10.18255/1818-1015-2021-3-292-311}
Linking options:
  • https://www.mathnet.ru/eng/mais751
  • https://www.mathnet.ru/eng/mais/v28/i3/p292
  • This publication is cited in the following 1 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Моделирование и анализ информационных систем
    Statistics & downloads:
    Abstract page:138
    Full-text PDF :62
    References:34
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024