Related papers: BanglaNirTox: A Large-scale Parallel Corpus for Ex…

Large Language Models (LLM) have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel…

Offensive Language detection in social media platforms has been an active field of research over the past years. In non-native English spoken countries, social media users mostly use a code-mixed form of text in their posts/comments. This…

Tokenization is a critical preprocessing step for large language models (LLMs), directly impacting training efficiency and downstream performance. General-purpose tokenizers trained predominantly on English and Latin-script languages…

Pre-training data shapes a language model's quality, but raw web text is noisy and demands careful cleaning. Existing large-scale corpora rely on English-centric or language-agnostic pipelines whose heuristics do not capture Thai script or…

Large Language Models (LLMs) perform exceedingly well in Natural Language Understanding (NLU) tasks for many languages including English. However, despite being the fifth most-spoken language globally, Grammatical Error Correction (GEC) in…

While Bangla is considered a language with limited resources, sentiment analysis has been a subject of extensive research in the literature. Nevertheless, there is a scarcity of exploration into sentiment analysis specifically in the realm…

Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting growing challenges for content moderation. Some users evade censorship by deliberately disguising…

The Internet is currently the largest platform for global communication including expressions of opinions, reviews, contents, images, videos and so forth. Moreover, social media has now become a very broad and highly engaging platform due…

While Large Language Models (LLM) have created a massive technological impact in the past decade, allowing for human-enabled applications, they can produce output that contains stereotypes and biases, especially when using low-resource…

Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Language is a deep-rooted means of perpetration of stereotypes and discrimination. Large Language Models (LLMs), now a pervasive technology in our everyday lives, can cause extensive harm when prone to generating toxic responses. The…

Large Language Models (LLMs) show impressive performance on many NLP benchmarks, yet their ability to reason in figurative, culturally grounded, and low-resource settings remains underexplored. We address this gap for Bangla by introducing…

Representing words and phrases into dense vectors of real numbers which encode semantic and syntactic properties is a vital constituent in natural language processing (NLP). The success of neural network (NN) models in NLP largely rely on…

The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment…

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020; Krause et al. 2020) have been proposed to mitigate toxic LM…

This paper is devoted to the adaptation of generative large language models for the Tajik language, a low-resource language with Cyrillic script. To overcome the shortage of digital text resources, the author created and publicly released…

Code-mixing is the phenomenon of using more than one language in a sentence. It is a very frequently observed pattern of communication on social media platforms. Flexibility to use multiple languages in one text message might help to…

One of the most popular downstream tasks in the field of Natural Language Processing is text classification. Text classification tasks have become more daunting when the texts are code-mixed. Though they are not exposed to such text during…

Bangla is the 7th most widely spoken language globally, with a staggering 234 million native speakers primarily hailing from India and Bangladesh. This morphologically rich language boasts a rich literary tradition, encompassing diverse…