Saved in:
Bibliographic Details
Main Authors: Bulatov, Victor, Alekseev, Vasiliy, Vorontsov, Konstantin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.10402
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910546445467648
author Bulatov, Victor
Alekseev, Vasiliy
Vorontsov, Konstantin
author_facet Bulatov, Victor
Alekseev, Vasiliy
Vorontsov, Konstantin
contents The number of topics might be the most important parameter of a topic model. The topic modelling community has developed a set of various procedures to estimate the number of topics in a dataset, but there has not yet been a sufficiently complete comparison of existing practices. This study attempts to partially fill this gap by investigating the performance of various methods applied to several topic models on a number of publicly available corpora. Further analysis demonstrates that intrinsic methods are far from being reliable and accurate tools. The number of topics is shown to be a method- and a model-dependent quantity, as opposed to being an absolute property of a particular corpus. We conclude that other methods for dealing with this problem should be developed and suggest some promising directions for further research.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10402
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Determination of the Number of Topics Intrinsically: Is It Possible?
Bulatov, Victor
Alekseev, Vasiliy
Vorontsov, Konstantin
Computation and Language
Information Retrieval
Probability
The number of topics might be the most important parameter of a topic model. The topic modelling community has developed a set of various procedures to estimate the number of topics in a dataset, but there has not yet been a sufficiently complete comparison of existing practices. This study attempts to partially fill this gap by investigating the performance of various methods applied to several topic models on a number of publicly available corpora. Further analysis demonstrates that intrinsic methods are far from being reliable and accurate tools. The number of topics is shown to be a method- and a model-dependent quantity, as opposed to being an absolute property of a particular corpus. We conclude that other methods for dealing with this problem should be developed and suggest some promising directions for further research.
title Determination of the Number of Topics Intrinsically: Is It Possible?
topic Computation and Language
Information Retrieval
Probability
url https://arxiv.org/abs/2406.10402