相关论文: Pagsusuri ng RNN-based Transfer Learning Technique…

This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resource language as part of an automated machine translation…

In recent years, transformer models have achieved great success in natural language processing (NLP) tasks. Most of the current state-of-the-art NLP results are achieved by using monolingual transformer models, where the model is…

Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases…

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 central bottleneck for low-resource NLP is typically regarded to be the quantity of accessible data, overlooking the contribution of data quality. This is particularly seen in the development and evaluation of low-resource systems via…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

Large Language Models (LLMs) excel in high-resource languages but struggle with low-resource languages due to limited training data. This paper presents TALL (Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages),…

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…

Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a…

Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approaches treat different source tasks equally, ignoring the…

We compare phone labels and articulatory features as input for cross-lingual transfer learning in text-to-speech (TTS) for low-resource languages (LRLs). Experiments with FastSpeech 2 and the LRL West Frisian show that using articulatory…

Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in…

Considering the importance of detecting hateful language, labeled hate speech data is expensive and time-consuming to collect, particularly for low-resource languages. Prior work has demonstrated the effectiveness of cross-lingual transfer…

High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech…

Neural Machine Translation (NMT) has seen a tremendous spurt of growth in less than ten years, and has already entered a mature phase. While considered as the most widely used solution for Machine Translation, its performance on…

Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation. While the Transformer model has achieved significant improvements for many language pairs and has…

Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is challenging to train…

Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected…

The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries. Building a neural machine translation (NMT) system has become an urgent…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…