Inclusive bidirectional conversion system between Chittagonian and standard Bangla

Abstract

In recent years, the Bangla language has come out as a very prominent figure in the world of natural language processing. Many researchers have produced exemplary works on the language, but there has not been any notable work on its highly enriched dialects due to the lack of resources and the diversity and complexity in its grammatical structure. This paper has suggested a bidirectional conversion system for one of the most widely used dialects of Bangla; the Chittagonian dialect. Our method employs a bidirectional lexicon that uses binary search, word-to-word mapping, and morphological transformations. The system has achieved an accuracy rate of 95.86% for Chittagonian to standard Bangla and 93.89% in the case of standard Bangla to Chittagonian. We have also provided an efficient word suggestion module, and it has yielded satisfactory results.

An improved extrinsic monolingual plagiarism detection approach of the Bengali text

“…A word that does not contain any meaningful information in a sentence is called a stop word [9], [30]. In Bengali, these types of stop words are এবং (and), ইহা (it), অক্ষ েক (many), তািপি (then).…”

“…The approach is based on non-trainable Gabor filters fused convolutional neural network (CNN). Hossain et al [9] proposed a bidirectional conversion system between Chittagonian and standard Bangla. Using binary search, word-to-word mapping, and morphological transformation developed a bidirectional lexicon.…”