相关论文: Phonology-Augmented Statistical Framework for Mach…

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

In this paper, we introduce a novel approach to generate synthetic data for training Neural Machine Translation systems. The proposed approach transforms a given parallel corpus between a written language and a target language to a parallel…

Cross-lingual adaptation, a special case of domain adaptation, refers to the transfer of classification knowledge between two languages. In this article we describe an extension of Structural Correspondence Learning (SCL), a recently…

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

In this paper, we aimed to develop a neural parser for Vietnamese based on simplified Head-Driven Phrase Structure Grammar (HPSG). The existing corpora, VietTreebank and VnDT, had around 15% of constituency and dependency tree pairs that…

Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural…

Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or…

Any approach aimed at pasteurizing and quantifying a particular phenomenon must include the use of robust statistical methodologies for data analysis. With this in mind, the purpose of this study is to present statistical approaches that…

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written. We collected a significant number of…

Machine Transliteration provides the ability to transliterate a basic language into different languages in a computational way. Transliteration is an important technical process that has caught the attention most recently. The Sinhala…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source…

Multilingual automatic lyrics transcription (ALT) is a challenging task due to the limited availability of labelled data and the challenges introduced by singing, compared to multilingual automatic speech recognition. Although some…

We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…

Synthetic data has become a cornerstone for scaling large language models, yet its multilingual use remains bottlenecked by translation-based prompts. This strategy inherits English-centric framing and style and neglects cultural…