Related papers: AxomiyaBERTa: A Phonologically-aware Transformer M…
Ransomware continues to evolve in complexity, making early and explainable detection a critical requirement for modern cybersecurity systems. This study presents a comparative analysis of three Transformer-based Large Language Models (LLMs)…
The development of monolingual language models for low and mid-resource languages continues to be hindered by the difficulty in sourcing high-quality training data. In this study, we present a novel cross-lingual vocabulary transfer…
We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…
Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…
Using token representation from bidirectional language models (LMs) such as BERT is still a widely used approach for token-classification tasks. Even though there exist much larger unidirectional LMs such as Llama-2, they are rarely used to…
Climate change is one of the most significant challenges we face together as a society. Creating awareness and educating policy makers the wide-ranging impact of climate change is an essential step towards a sustainable future. Recently,…
Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…
Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional way of LM training treats all the words in corpora equally, resulting in…
Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to…
Figures of Speech (FoS) consist of multi-word phrases that are deeply intertwined with culture. While Neural Machine Translation (NMT) performs relatively well with the figurative expressions of high-resource languages, it often faces…
Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference. However, previous studies have claimed that this form of subword tokenization is inadequate for…
Language model (LM) pretraining can learn various knowledge from text corpora, helping downstream tasks. However, existing methods such as BERT model a single document, and do not capture dependencies or knowledge that span across…
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…
With the advent of the Transformer architecture, Neural Machine Translation (NMT) results have shown great improvement lately. However, results in low-resource conditions still lag behind in both bilingual and multilingual setups, due to…
Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models such as wav2vec2 and large-scale multi-lingual training like Whisper. A huge…
Recent advances have enabled Large Language Models (LLMs) to tackle reasoning tasks by generating chain-of-thought (CoT) rationales, yet these gains have largely applied to high-resource languages, leaving low-resource languages behind. In…
Effective instruction fine-tuning on diverse image-text datasets is crucial for developing a versatile Multimodal Large Language Model (MLLM), where dataset composition dictates the model's adaptability across multimodal tasks. However,…
Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in modern NLP. It has been observed that fine-tuning these models on…
Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by implementing a lattice rescoring or $n$-best re-ranking. While pretraining with a…
In our increasingly interconnected digital world, social media platforms have emerged as powerful channels for the dissemination of hate speech and offensive content. This work delves into the domain of hate speech detection, placing…