Large language models (LLMs) have demonstrated impressive capabilities in general
scenarios, exhibiting a level of aptitude that approaches, in some aspects even surpasses …

Abstract Machine Translation (MT) has made significant progress in recent years using deep
learning, especially after the emergence of large language models (LLMs) such as GPT-3 …

Text watermarking technology aims to tag and identify content produced by large language
models (LLMs) to prevent misuse. In this study, we introduce the concept of cross-lingual …

Insufficient modeling of human preferences within the reward model is a major obstacle for
leveraging human feedback to improve translation quality. Fortunately, quality estimation …

Visual features encompass visual information extracted from images or videos, serving as
supplementary input to enhance the efficacy of neural machine translation (NMT) systems …

Abstract Multilingual Neural Machine Translation (MNMT) has recently made great progress
in training models that can translate between multiple languages. However, MNMT faces a …

Neural networks are capable of translating between languages—in some cases even
between two languages where there is little or no access to parallel translations, in what is …

Low-resource machine translation struggles over the issue of bilingual data sparsity. Self-
training based bilingual data augmentation is potentially useful for overcoming the issue …

Minimizing social bias strengthens societal bonds, promoting shared understanding and
better decision-making. We revisit the definition of bias by discovering new bias types (eg …

This study proposes an unsupervised machine translation method based on a dynamic
adaptive masking strategy and multi-task learning. Firstly, a dynamic adaptive masking …