Mohammad Abdullah Al Mumin

• Professor at Shahjalal University of Science and Technology

The purpose of this study is to assess the sentiment (tone) of people toward various governmental decisions, which therefore assists the government in assessing how people think about any particular decision. In this study, a total of 7645 comments were collected and pre-possessed, and labels were given in three polarities (positive, negative, and...

Due to the enormous growth of information and technology, the digitized texts and data are being immensely generated. Therefore, identifying the main topics in a vast collection of documents by humans is merely impossible. Topic modeling is such a statistical framework that infers the latent and underlying topics from text documents, corpus, or ele...

The recent conception about the network and communication framework is going to update in the upcoming years. It is expected that the number of connected devices worldwide is going to take control of our daily life. The growth of IoT devices made it possible. For comforting human life, the Internet of Things (IoT) forms a huge network to produce be...

Document clustering is a machine learning approach to categorize documents into related groups without any definition to the documents prior to the process. It helps to categorize very large chunks of documents into similar categories for making the process of finding a particular document easier. It also helps in retrieval of the data. There has b...

Neural machine translation has recently been able to gain state-of-the-art translation quality for many language pairs. However, neural machine translation has been less tested for English-Bangla language pair, two linguistically distant and widely spoken languages. In this paper, we apply neural machine translation to the task of English-Bangla tr...

An efficient and publicly open machine translation system is in dire need to get the maximum benefits of Information and Communication Technology through removing the language barrier in this era of globalization. In this study, we present a Phrase-Based Statistical Machine Translation (PBMT) system between English and Bangla languages in both dire...

English-Bangla machine translation is a challenging task as the languages differ in syntactic structure and morphological complexity. The standard phrase-based statistical machine translation (SMT) is unable to capture these linguistic difference because they lack any explicit use of linguistic information, be it morphological, syntactic, or semant...

Question answering (QA) system enables users to retrieve exact answers for questions asked in natural language. The QA task has made considerable progress recently with the advent of deep learning architectures, which does not depend on manually defined features or linguistic tools. In order to apply these training data-intensive, expressive deep...

Recent works have shown neural network based language model to be an effective language modeling technique in statistical machine translation (SMT), outperforming standard n-gram back-off language model. For English-Bangla SMT, however, the performance of the neural language model has not been well explored. In this work, we propose a novel approac...

This work presents a detailed approach of automatic keyword extraction from Bangla scientific documents using a hybrid method, which utilizes both unsupervised and supervised machine learning model. This is a novel method as no previous Bangla keyword extraction method used the strengths of the unsupervised and supervised model together which are t...

This paper develops an algorithm for making an automated Bangla Parts Of Speech (POS) tagged dictionary. Natural Language Processing is one of the most vigorous research areas of computer science. It enables to communicate and retrieve information form computer based system more effectively and efficiently. Researches on Bangla language processing...

The development of Language Engineering applications requires availability of sizable, reliable and representative corpora. However, such corpora are not routinely available for Bengali language. This paper introduces Shahjalal University Monolingual (SUMono) corpus, a representative modern Bengali corpus consisting of more than 27 million words, w...

The lexical tags, called Tagsets, play a significant role providing the large amount of information about a word and its neighbors, telling us something about how the words are pronounced, being used in stemming for information retrieval[1]. So, a standard tagset is necessary for working with a language in any computational linguistic field. Two ma...

Parallel corpora have become an essential resource in natural language processing. In spite of their importance in many multilingual applications, a few effective English-Bengali corpus has been made available, given the scarcity of its resources and the intensive lobors required in its creation. This paper introduces Shahjalal University Parallel...

This paper is intended to present some important theoretical and experimental result that we have faced during setting up a VoIP (voice over Internet protocol) server with the well known open source VoIP server Asterisk@Home. The first part of the paper presents the project objective with some introductory theory about VoIP. The second part contain...

This paper describes an implementation process of a Machine Translation (MT) system between Bangla and English. Transfer based Linguistic Knowledge (LK) architecture is preferred to implement this architecture. ln this system we have used Lexical Functional Grammar (LFG) frameworks to define the Bangla and English grammar. A functional specificatio...