Related papers: Character-Level Bangla Text-to-IPA Transcription U…

Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…

This paper presents an optimal Bangla Keyboard Layout, which distributes the load equally on both hands so that maximizing the ease and minimizing the effort. Bangla alphabet has a large number of letters, for this it is difficult to type…

Bengali is an underrepresented language in NLP research. However, it remains a challenge due to its unique linguistic structure and computational constraints. In this work, we systematically investigate the challenges that hinder Bengali…

Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little…

Text classification has become a crucial task in various fields, leading to a significant amount of research on developing automated text classification systems for national and international languages. However, there is a growing need for…

Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks such as text classification, question-answering, and token classification. However, this performance is usually…

Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture…

Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target…

People commonly communicate in English, Arabic, and Bengali spoken languages through various mediums. However, deaf and hard-of-hearing individuals primarily use body language and sign language to express their needs and achieve…

In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. Due to computational constraints during both training and inference, we focused on smaller models. To train TituLLMs, we…

Log parsing is a critical standard operating procedure in software systems, enabling monitoring, anomaly detection, and failure diagnosis. However, automated log parsing remains challenging due to heterogeneous log formats, distribution…

Code-switching and language identification in child-directed scenarios present significant challenges, particularly in bilingual environments. This paper addresses this challenge by using Zipformer to handle the nuances of speech, which…

Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing…

Language modeling has witnessed remarkable advancements in recent years, with Large Language Models (LLMs) like ChatGPT setting unparalleled benchmarks in human-like text generation. However, a prevailing limitation is the…

While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited. Directly fine-tuning such language…

This paper presents an Arabic Alphabet Sign Language recognition approach, using deep learning methods in conjunction with transfer learning and transformer-based models. We study the performance of the different variants on two publicly…

Bengali text classification is a Significant task in natural language processing (NLP), where text is categorized into predefined labels. Unlike English, Bengali faces challenges due to the lack of extensive annotated datasets and…

Characters are the smallest unit of text that can extract stylometric signals to determine the author of a text. In this paper, we investigate the effectiveness of character-level signals in Authorship Attribution of Bangla Literature and…

Gloss is a written approximation that bridges Sign Language (SL) and its corresponding spoken language. Despite a deaf and hard-of-hearing population of at least 3 million in Bangladesh, Bangla Sign Language (BdSL) remains largely…

A lot of search approaches have been explored for the selection of features in pattern classification domain in order to discover significant subset of the features which produces better accuracy. In this paper, we introduced a Harmony…