Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment
Multilingual knowledge graph (KG) embeddings provide latent semantic representations of
entities and structured knowledge with cross-lingual inferences, which benefit various …
entities and structured knowledge with cross-lingual inferences, which benefit various …
Self-paced multi-view co-training
Co-training is a well-known semi-supervised learning approach which trains classifiers on
two or more different views and exchanges pseudo labels of unlabeled instances in an …
two or more different views and exchanges pseudo labels of unlabeled instances in an …
System of robot learning from multi-modal demonstration and natural language instruction
S Lu, J Berger, J Schilp - Procedia CIRP, 2022 - Elsevier
Collaborative robots are set to play an important role in the future of the manufacturing
industry. They need to be able to work outside of the fencing and perform new tasks to …
industry. They need to be able to work outside of the fencing and perform new tasks to …
Efficient co-training of linear separators under weak dependence
We develop the first polynomial-time algorithm for co-training of homogeneous linear
separators under\em weak dependence, a relaxation of the condition of independence …
separators under\em weak dependence, a relaxation of the condition of independence …
[BOOK][B] Learning from Imperfect Supervision in Visual Pattern Classification and Localization
F Ma - 2022 - search.proquest.com
Abstract Machine learning algorithms have achieved tremendous success on various
computer vision tasks in past decades. Large-scale well-annotated data, such as ImageNet …
computer vision tasks in past decades. Large-scale well-annotated data, such as ImageNet …
Transfer of Models and Resources for Under-Resourced Languages Semantic Role Labeling
Y Mohamed, W Menzel - Pan African Conference on Artificial Intelligence, 2023 - Springer
Identifying and labeling the semantic roles of words and phrases within a sentence is a
crucial task in the field of natural language processing (NLP), known as semantic role …
crucial task in the field of natural language processing (NLP), known as semantic role …
[BOOK][B] Multi-relational Representation Learning and Knowledge Acquisition
M Chen - 2019 - search.proquest.com
Multi-relational representation learning methods encode entities or concepts of a knowledge
graph in a continuous and low-dimensional vector space, where the relational inferences of …
graph in a continuous and low-dimensional vector space, where the relational inferences of …