Related papers: Unsupervised Domain Adaptation of Contextualized E…

Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain…

Recent advances in pre-trained language modeling have facilitated significant progress across various natural language processing (NLP) tasks. Word masking during model training constitutes a pivotal component of language modeling in…

Reading comprehension (RC) has been studied in a variety of datasets with the boosted performance brought by deep neural networks. However, the generalization capability of these models across different domains remains unclear. To alleviate…

Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled…

Domain adaptation approaches seek to learn from a source domain and generalize it to an unseen target domain. At present, the state-of-the-art unsupervised domain adaptation approaches for subjective text classification problems leverage…

Social media such as Twitter provide valuable information to crisis managers and affected people during natural disasters. Machine learning can help structure and extract information from the large volume of messages shared during a crisis;…

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been…

Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based…

We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight…

Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks. Through training on one hundred languages…

BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

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,…