Results 11 to 20 of about 1,180,741 (266)
The relation between metaphor and impoliteness in the context of interpersonal media gossip [PDF]
The present study aims at examining the possible relation between metaphor and impoliteness in the context of interpersonal media gossip. To this end, we collected data related to 20 celebrities (10 actors and 10 actresses) regarding 60 linguistic ...
Seyede Sahar Javid +3 more
doaj +1 more source
Improving Domain Adaptation by Source Selection [PDF]
Domain adaptation consists in learning from a source data distribution a model that will be used on a different target data distribution. The domain adaptation procedure is usually unsuccessful if the source domain is too different from the target one. In this paper, we study domain adaptation for image classification with deep learning in the context ...
Bascol, Kevin +2 more
openaire +1 more source
Is Beauty Just Force? A Corpus-Based Metaphor Analysis
It is well known that beauty is important for the conceptualization of love (Kövecses,1986). This study aims to determine how beauty is conceptualized. In particular, using a corpus consisting of 73,268 tokens, we investigate what metaphors of beauty are
Mehmet AYGÜNEŞ
doaj +1 more source
Conceptual metaphors in North African French-speaking news discourse about COVID-19
Conceptual metaphors have received much attention in research on discourse about infectious diseases in recent years. Most studies found that conceptual metaphors of war dominate media discourse about disease. Similarly, a great deal of research has been
Hicham Lahlou, Hajar Abdul Rahim
doaj +1 more source
Gated Domain Units for Multi-source Domain Generalization.
ISSN:2835 ...
Simon Föll +9 more
openaire +4 more sources
Interaction of comparative structures and their elements in modern russian prose
The article explores the interaction of comparative constructions in modern prose. The main objective of the study is to determine the types of interaction between metaphors and similes in the texts of modern Russian prose.
Natalia A. Nikolina +2 more
doaj +1 more source
Multi-Source Distilling Domain Adaptation
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution.
Sicheng Zhao +9 more
openaire +3 more sources
Curriculum Manager for Source Selection in Multi-source Domain Adaptation [PDF]
The performance of Multi-Source Unsupervised Domain Adaptation depends significantly on the effectiveness of transfer from labeled source domain samples. In this paper, we proposed an adversarial agent that learns a dynamic curriculum for source samples, called Curriculum Manager for Source Selection (CMSS).
Luyu Yang +3 more
openaire +2 more sources
Discovering Domain Disentanglement for Generalized Multi-Source Domain Adaptation
A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain. Nevertheless, prior works strictly assume that each source domain shares the identical group of classes with the target domain, which could hardly be guaranteed as the target label space is not
Zixin Wang +4 more
openaire +3 more sources
Generalized Source-free Domain Adaptation [PDF]
Accepted by ICCV 2021; Update the acknowledgement ...
Shiqi Yang 0002 +4 more
openaire +2 more sources

