Related papers: FGraDA: A Dataset and Benchmark for Fine-Grained D…
Continuously-growing data volumes lead to larger generic models. Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. Our work addresses this gap with a method for selecting…
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the labeled data may be collected from multiple sources,…
Machine translation (MT) systems, especially when designed for an industrial setting, are trained with general parallel data derived from the Web. Thus, their style is typically driven by word/structure distribution coming from the average…
Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on…
While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain…
Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate…
Foundation models (FMs) have shown prominent success in a wide range of tasks. Their applicability to specific domain-task pairings relies on the availability of, both, high-quality data and significant computational resources. These…
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…
Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source domain (e.g. synthetic data) to the target domain (e.g. real-world data) without requiring further annotations on the target domain. This work focuses on UDA…
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a…
One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation…
Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may differ significantly…
Domain adaptation techniques have contributed to the success of deep learning. Leveraging knowledge from an auxiliary source domain for learning in labeled data-scarce target domain is fundamental to domain adaptation. While these…
In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural language processing. To better leverage the potential of…
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical machine translation has shown that extending the basic…
Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of…
The increasing volume of scientific research necessitates effective communication across language barriers. Machine translation (MT) offers a promising solution for accessing international publications. However, the scientific domain…
Finetuning language models for a new domain inevitably leads to the deterioration of their general performance. This becomes more pronounced the more limited the finetuning data resource. We introduce minifinetuning (MFT), a method for…
While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in. As a result, people often…
In the settings of conventional domain adaptation, categories of the source dataset are from the same domain (or domains for multi-source domain adaptation), which is not always true in reality. In this paper, we propose…