Related papers: Phonology-Augmented Statistical Framework for Mach…
This study introduces an innovative automatic labeling framework to address the challenges of lexical normalization in social media texts for low-resource languages like Vietnamese. Social media data is rich and diverse, but the evolving…
Spelling error correction is one of topics which have a long history in natural language processing. Although previous studies have achieved remarkable results, challenges still exist. In the Vietnamese language, a state-of-the-art method…
Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation…
Large Language Models (LLMs), with gradually improving reading comprehension and reasoning capabilities, are being applied to a range of complex language tasks, including the automatic generation of language data for various purposes.…
One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…
The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the…
Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited…
Although the curse of multilinguality significantly restricts the language abilities of multilingual models in monolingual settings, researchers now still have to rely on multilingual models to develop state-of-the-art systems in Vietnamese…
Word segmentation is a basic problem in natural language processing. With the languages having the complex writing system like the Khmer language in Southern of Vietnam, this problem really very intractable, posing the significant…
Most Automatic Speech Recognition (ASR) systems formulate transcription as a prediction problem over orthographic units such as characters, subwords, or words. Although effective, such representations do not explicitly reflect the phonetic…
Most statistical machine translation systems cannot translate words that are unseen in the training data. However, humans can translate many classes of out-of-vocabulary (OOV) words (e.g., novel morphological variants, misspellings, and…
Machine Translation is one of the essential tasks in Natural Language Processing (NLP), which has massive applications in real life as well as contributing to other tasks in the NLP research community. Recently, Transformer -based methods…
The quality of a multilingual speech recognition system can be improved by adaptation methods if the input language is specified. For systems that can accept multilingual inputs, the popular approach is to apply a language identifier to the…
The lack of parallel data for many language pairs is an important challenge to statistical machine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target…
Most of the recent work on terminology integration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the target language sentence. In day-to-day work of professional…
In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in…
Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics.…
Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training. This paper proposes two simple strategies to address the rare…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
Semantic parsing is an important NLP task. However, Vietnamese is a low-resource language in this research area. In this paper, we present the first public large-scale Text-to-SQL semantic parsing dataset for Vietnamese. We extend and…