The Experts below are selected from a list of 21 Experts worldwide ranked by ideXlab platform
Yu Zhao - One of the best experts on this subject based on the ideXlab platform.
-
Learning three-way affinity embeddings for knowledge base completion
2016 8th IEEE International Conference on Communication Software and Networks (ICCSN), 2016Co-Authors: Yu ZhaoAbstract:Knowledge bases are an extremely important database for knowledge management, which is very useful for question Answering, Query expansion and other related tasks. However, it often suffers from incompleteness. In this paper, we propose a Three-Way Affinity Embeddings model (TWAE) to map both the entity and relationship into two vectors and consider any two of them direct interaction, and then predict the possible truth of additional facts. The basic idea is that the confidence of the additional predicted fact is determined by three-way affinities in the triplet using the latent representation of each item. Experiments show that our model performs excellent.
-
A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Computación y sistemas, 2016Co-Authors: Yu Zhao, Sheng Gao, Patrick Gallinari, Jun GuoAbstract:Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.
Jun Guo - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Computación y sistemas, 2016Co-Authors: Yu Zhao, Sheng Gao, Patrick Gallinari, Jun GuoAbstract:Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.
Sheng Gao - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Computación y sistemas, 2016Co-Authors: Yu Zhao, Sheng Gao, Patrick Gallinari, Jun GuoAbstract:Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.
Patrick Gallinari - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Computación y sistemas, 2016Co-Authors: Yu Zhao, Sheng Gao, Patrick Gallinari, Jun GuoAbstract:Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.
Wu Ting - One of the best experts on this subject based on the ideXlab platform.
-
Answering Query Through Cache During Disconnection
Chinese Journal of Computers, 2020Co-Authors: Wu TingAbstract:Because of the characteristic of wireless networks and mobile units in mobile environments, the mobile computer has to be disconnected often by the user or by accident. During disconnection, clients have no access to networks and can only access information in the local cache. In this paper, we propose a Query processing algorithm QPID (Query Processing In Disconnection) based on semantic caches. Semantic cache is a cache that explores the semantic locality among client-issued queries and is composed of former Query results and descriptions. In order to provide better support for clients to access data during disconnection and to utilize cache more effectively, QPID algorithm satisfies a Query by several cache items. The main idea is to find cache items related to the Query first, classify them into direct-related and indirect-related cache items, then process data corresponding to these cache items to get Query result. Whether equivalent Query answer is obtained is determined by the descriptions of cache items and the Query. Experiments show that based on QPID algorithm, semantic cache can be used more effectively and more client queries can be answered during disconnection.