Related papers: Empowering Bengali Education with AI: Solving Beng…

We study the performance of a commercially available large language model (LLM) known as ChatGPT on math word problems (MWPs) from the dataset DRAW-1K. To our knowledge, this is the first independent evaluation of ChatGPT. We found that…

Intent classification is a fundamental task in natural language understanding, aiming to categorize user queries or sentences into predefined classes to understand user intent. The most challenging aspect of this particular task lies in…

This paper presents a high-quality dataset for evaluating the quality of Bangla word embeddings, which is a fundamental task in the field of Natural Language Processing (NLP). Despite being the 7th most-spoken language in the world, Bangla…

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Bangla is the sixth most widely spoken language globally, with approximately 234 million native speakers. However, progress in open-source Bangla machine translation remains limited. Most online resources are in English and often remain…

Sentiment analysis is the process of identifying and categorizing people's emotions or opinions regarding various topics. Analyzing political sentiment is critical for understanding the complexities of public opinion processes, especially…

Bengali is one of the most spoken languages in the world with over 300 million speakers globally. Despite its popularity, research into the development of Bengali speech recognition systems is hindered due to the lack of diverse open-source…

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual…

The recent advances in deep-learning have led to the development of highly sophisticated systems with an unquenchable appetite for data. On the other hand, building good deep-learning models for low-resource languages remains a challenging…

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

While machine translation is regarded as a "solved problem" for many high-resource languages, close analysis quickly reveals that this is not the case for content that shows challenges such as poetic language, philosophical concepts,…

Recent advancements in NLP have given us models like mBERT and XLMR that can serve over 100 languages. The languages that these models are evaluated on, however, are very few in number, and it is unlikely that evaluation datasets will cover…

Sociotechnical systems, such as language technologies, frequently exhibit identity-based biases. These biases exacerbate the experiences of historically marginalized communities and remain understudied in low-resource contexts. While models…

Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings. To address these challenges, we propose mmT5, a modular…

Large Language Models (LLMs) have been applied to Math Word Problems (MWPs) with transformative impacts, revolutionizing how these complex problems are approached and solved in various domains including educational settings. However, the…

Large language models (LLMs) have exhibited great potential in mathematical reasoning. However, there remains a performance gap in this area between existing open-source models and closed-source models such as GPT-4. In this paper, we…

This paper presents the system description of Machine Translation (MT) system(s) for Indic Languages Multilingual Task for the 2018 edition of the WAT Shared Task. In our experiments, we (the RGNLP team) explore both statistical and neural…

Transformers are widely used in NLP tasks. However, current approaches to leveraging transformers to understand language expose one weak spot: Number understanding. In some scenarios, numbers frequently occur, especially in semi-structured…

Grounding vision--language models in low-resource languages remains challenging, as they often produce fluent text about the wrong objects. This stems from scarce paired data, translation pivots that break alignment, and English-centric…

Retrosynthesis analysis is pivotal yet challenging in drug discovery and organic chemistry. Despite the proliferation of computational tools over the past decade, AI-based systems often fall short in generalizing across diverse reaction…