Related papers: Contextual Spelling Correction with Language Model…
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…
Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models still struggle in other areas, such as personalization towards…
One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…
Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors. Recently, related researches focus on introducing character similarity from confusion set to enhance the CSC models, ignoring the context of characters…
In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. There has been recent interest in investigating approaches for training systems for languages with limited resources and…
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…
Contextual Embeddings have yielded state-of-the-art results in various natural language processing tasks. However, these embeddings are constrained by models requiring large amounts of data and huge computing power. This is an issue for…
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…
The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learning of short range dependencies, which generally model the…
In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…
This work proposes a simple training-free prompt-free approach to leverage large language models (LLMs) for the Chinese spelling correction (CSC) task, which is totally different from all previous CSC approaches. The key idea is to use an…
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a…
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…
In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…
Modelling a language model for a multi-lingual scenario includes several potential challenges, among which catastrophic forgetting is the major challenge. For example, small language models (SLM) built for low-resource languages by adapting…
Lack of proper linguistic resources is the major challenges faced by the Machine Translation system developments when dealing with the resource poor languages. In this paper, we describe effective ways to utilize the lexical resources to…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
Grammatical error correction (GEC) is an important task in Natural Language Processing that aims to automatically detect and correct grammatical mistakes in text. While recent advances in transformer-based models and large annotated…
This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…