Related papers: Text Generation Models for Luxembourgish with Limi…
Current large language models (LLMs) are trained on massive amounts of text data, primarily from a few dominant languages. Studies suggest that this over-reliance on high-resource languages, such as English, hampers LLM performance in mid-…
Concept-to-text Natural Language Generation is the task of expressing an input meaning representation in natural language. Previous approaches in this task have been able to generalise to rare or unseen instances by relying on a…
Large Language Models (LLMs) are pretrained on textual data up to a specific temporal cutoff. This creates a strict knowledge boundary beyond which models cannot provide accurate information without querying external sources. More subtly,…
State-of-the-art vision-and-language models consist of many parameters and learn from enormous datasets, surpassing the amounts of linguistic data that children are exposed to as they acquire a language. This paper presents our approach to…
Lexicon or dictionary generation across domains has the potential for societal impact, as it can potentially enhance information accessibility for a diverse user base while preserving language identity. Prior work in the field primarily…
Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning,…
Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…
Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-resource languages, especially in privacy-sensitive and…
While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma…
The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…
Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes, where people and landmarks originate from different cultures, remains largely…
State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating those vocabularies are not ideal for massively multilingual…
Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Through improvements in multilingual…
The development of Large Language Models (LLMs) has predominantly focused on high-resource languages, leaving extremely low-resource languages like Irish with limited representation. This work presents UCCIX, a pioneering effort on the…
Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of incorporating…
Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We…
Multilingual language models such as mBERT have seen impressive cross-lingual transfer to a variety of languages, but many languages remain excluded from these models. In this paper, we analyse the effect of pre-training with monolingual…
In this paper,we explore the application of Back translation (BT) as a semi-supervised technique to enhance Neural Machine Translation(NMT) models for the English-Luganda language pair, specifically addressing the challenges faced by…
Monolingual data, being readily available in large quantities, has been used to upscale the scarcely available parallel data to train better models for automatic translation. Self-learning, where a model is made to learn from its output, is…
The increasing size and complexity of pre-trained language models have demonstrated superior performance in many applications, but they usually require large training datasets to be adequately trained. Insufficient training sets could…