Related papers: Towards a general purpose machine translation syst…
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…
Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have…
Around seven million individuals in India, Bangladesh, Bhutan, and Nepal speak Santali, positioning it as nearly the third most commonly used Austroasiatic language. Despite its prominence among the Austroasiatic language family's Munda…
In this paper, we explore the utility of translationese as synthetic data created using machine translation for pre-training language models (LMs) for low-resource languages (LRLs). Our simple methodology consists of translating large…
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…
The Mayan languages comprise a language family with an ancient history, millions of speakers, and immense cultural value, that, nevertheless, remains severely underrepresented in terms of resources and global exposure. In this paper we…
End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining…
Large Language Models (LLMs) demonstrate impressive general knowledge and reasoning abilities, yet their evaluation has predominantly focused on global or anglocentric subjects, often neglecting low-resource languages and culturally…
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…
Multilingual Neural Machine Translation (MNMT) for low-resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about…
Neural approaches have achieved state-of-the-art accuracy on machine translation but suffer from the high cost of collecting large scale parallel data. Thus, a lot of research has been conducted for neural machine translation (NMT) with…
Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show promise for, e.g., improving low-resource machine translation…
This paper explores the potential of recurrent neural networks (RNNs) and other subquadratic architectures as competitive alternatives to transformer-based models in low-resource language modeling scenarios. We utilize HGRN2 (Qin et al.,…
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT…
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social…
Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…
Research on prompting has shown excellent performance with little or even no supervised training across many tasks. However, prompting for machine translation is still under-explored in the literature. We fill this gap by offering a…
We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual…
Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one…
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are…