Supervised learning Methods for Bangla Web Document Categorization

Mandal, Ashis Kumar; Sen, Rikta

doi:10.48550/arxiv.1410.2045

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We hope NLP and linguistic researchers of Bangla would find this corpus useful in different aspects of research on the Bangla language. [36] 0.98 0.98 0.98 98.33% Word2Vec (NN) [26] 0.96 0.96 0.96 96% TF-IDF* (NN) [26] 0.96 0.96 0.96 96% TF-IDF (SGD) [37] 0.92 0.92 0.92 92% TF-IDF (SVM) [37] 0.92 0.92 0.92 92% SVM [38] N/A N/A 0.89 89.14% Naive Bayes [38] N/A N/A 0.85 85.22% DenseNN2 [39] 0.85 0.85 0.85 85.20%…”

Section: Discussionmentioning

confidence: 99%

Compilation, Analysis and Application of a Comprehensive Bangla Corpus KUMono

et al. 2022

View full text Add to dashboard Cite

Research in Natural Language Processing (NLP) and computational linguistics highly depends on a good quality representative corpus of any specific language. Bangla is one of the most spoken languages in the world but Bangla NLP research is in its early stage of development due to the lack of quality public corpus. This article describes the detailed compilation methodology of a comprehensive monolingual Bangla corpus, KUMono. The newly developed corpus consists of more than 350 million word tokens and more than one million unique tokens from 18 major text categories of online Bangla websites. We have conducted several word-level and character-level linguistic phenomenon analyses based on empirical studies of the developed corpus. The corpus follows Zipf's curve and hapax legomena rule. The quality of the corpus is also assessed by analyzing and comparing the inherent sparseness of the corpus with existing Bangla corpora, by analyzing the distribution of function words of the corpus and vocabulary growth rate. We have developed a Bangla article categorization application based on the KUMono corpus and received compelling results by comparing to the state-of-the-art models.

show abstract

Section: Discussionmentioning

confidence: 99%

Compilation, Analysis and Application of a Comprehensive Bangla Corpus KUMono

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They have used two feature selection techniques namely Chi-square distribution and normalized TF-IDF with traditional machine learning classifiers such as Support Vector Machine(SVM), Naïve Bayes(NB) and Stochastic Gradient Descent(SGD). [22] employed four machine learning algorithms, including Support Vector Machine (SVM), Naive Bays, K-Nearest Neighbour (KNN), and Decision Tree for Bengali text classification. The dataset they used for their research was the BD corpus, which has 1000 documents and a total of 22,218 words.…”

Section: Literature Survey On Bengali Text Classificationmentioning

confidence: 99%

Bengali Text Classification: A New multi-class Dataset and Performance Evaluation of Machine Learning and Deep Learning Models

Roy

Sarkar

Mandal

2023

Preprint

View full text Add to dashboard Cite

This study focuses on Bengali text classification using machine learning and deep learning techniques. Text classification is a fundamental task in natural language processing (NLP) that involves categorizing text documents into predefined categories or classes. While text classification has received considerable attention in the English language, there is a limited amount of research specifically addressing Bengali text classification. This gap in the literature highlights the need for exploring and developing effective techniques tailored to the Bengali language. Furthermore, although some datasets for Bengali text classification tasks have been produced, most of the datasets have a limited number of labels. In our work, we introduce a new dataset for the Bengali text classification task, which has 38 class labels. The dataset includes data from the leading Bengali newspapers. We have evaluated many state-of-the-art machine learning and deep learning classification methods on our dataset to construct a benchmark that will facilitate future research.

show abstract