Related papers: Learning a Multi-Domain Curriculum for Neural Mach…

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model the two kinds of…

The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a…

We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used,…

Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation. However, little attention is paid to inaugurate more diverse context for…

Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval,…

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the…

While monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less explored area. In this work,…

Large Language Models (LLMs) have demonstrated remarkable abilities in general scenarios. Instruction finetuning empowers them to align with humans in various tasks. Nevertheless, the Diversity and Quality of the instruction data remain two…

Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…

Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (in domain) and dissimilar (out of domain) instances to those seen in…

This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set…

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…

The quality of machine translation is rapidly evolving. Today one can find several machine translation systems on the web that provide reasonable translations, although the systems are not perfect. In some specific domains, the quality may…

Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and…

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both the general-domain and in-domain. However, the existing methods for domain adaptation usually suffer…

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large…

Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should…

Automatic data selection and curriculum design for training large language models is challenging, with only a few existing methods showing improvements over standard training. Furthermore, current schemes focus on domain-level selection,…