期刊
AI IN COMPUTATIONAL LINGUISTICS
卷 189, 期 -, 页码 191-194出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.procs.2021.05.096
关键词
Topic modeling; BERT; BERTopic; LDA; NMF; NPMI; Arabic Language
Topic modeling is an unsupervised machine learning technique that helps find abstract topics in a large collection of documents. Popular techniques like LDA and NMF are used for this purpose, with emerging approaches using BERT-based methods gaining traction. Overall, the results from BERTopic outperformed NMF and LDA in this study.
Topic modeling is an unsupervised machine learning technique for finding abstract topics in a large collection of documents. It helps in organizing, understanding and summarizing large collections of textual information and discovering the latent topics that vary among documents in a given corpus. Latent Dirichlet allocation (LDA) and Non-Negative Matrix Factorization (NMF) are two of the most popular topic modeling techniques. LDA uses a probabilistic approach whereas NMF uses matrix factorization approach, however, new techniques that are based on BERT for topic modeling do exist. In this paper, we aim to experiment with BERTopic using different Pre-Trained Arabic Language Models as embeddings, and compare its results against LDA and NMF techniques. We used Normalized Pointwise Mutual Information (NPMI) measure to evaluate the results of topic modeling techniques. The overall results generated by BERTopic showed better results compared to NMF and LDA. (C) 2021 The Authors. Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据