Related papers: BanglaEmbed: Efficient Sentence Embedding Models f…
Each new generation of English-oriented Large Language Models (LLMs) exhibits enhanced cross-lingual transfer capabilities and significantly outperforms older LLMs on low-resource languages. This prompts the question: Is there a need for…
Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…
Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…
Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…
The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine…
Automatic Speech Recognition (ASR) transcripts, especially in low-resource languages like Bangla, contain a critical ambiguity: word-word repetitions can be either Repetition Disfluency (unintentional ASR error/hesitation) or Morphological…
The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…
Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few…
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…
The conventional natural language processing approaches are not accustomed to the social media text due to colloquial discourse and non-homogeneous characteristics. Significantly, the language identification in a multilingual document is…
Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods…
Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks. However, these methods are only available for limited languages due to relying heavily on the large NLI datasets. In…
We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…
Recent advances in Multilingual Large Language Models (MLLMs) have significantly enhanced cross-lingual conversational capabilities, yet modeling culturally nuanced and context-dependent communication remains a critical bottleneck.…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…
Spelling error correction is the task of identifying and rectifying misspelled words in texts. It is a potential and active research topic in Natural Language Processing because of numerous applications in human language understanding. The…
The selection of features for text classification is a fundamental task in text mining and information retrieval. Despite being the sixth most widely spoken language in the world, Bangla has received little attention due to the scarcity of…
As an Indo-Aryan language with limited available data, Chakma remains largely underrepresented in language models. In this work, we introduce a novel corpus of contextually coherent Bangla-transliterated Chakma, curated from Chakma…