Related papers: Task Transfer and Domain Adaptation for Zero-Shot …

The performance of automatic speech recognition models often degenerates on domains not covered by the training data. Domain adaptation can address this issue, assuming the availability of the target domain data in the target language.…

While neural networks have shown impressive performance on large datasets, applying these models to tasks where little data is available remains a challenging problem. In this paper we propose to use feature transfer in a zero-shot…

In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of…

Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading…

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before…

Conversational agents such as Alexa and Google Assistant constantly need to increase their language understanding capabilities by adding new domains. A massive amount of labeled data is required for training each new domain. While domain…

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem…

Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training…

In Information Retrieval, and more generally in Natural Language Processing, adapting models to specific domains is conducted through fine-tuning. Despite the successes achieved by this method and its versatility, the need for human-curated…

Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist…

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…

Domain adaptation is an important and widely studied problem in natural language processing. A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain. In this paper, we…

Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. Several approaches have beenproposed for classification tasks in the unsupervised scenario, where no labeled target…

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In…

This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work,…

We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new…

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

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…