Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ge, Xiou"'
Autor:
Ge, Xiou, Mousavi, Ali, Grave, Edouard, Joulin, Armand, Qian, Kun, Han, Benjamin, Arefiyan, Mostafa, Li, Yunyao
Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is complete. It is
Externí odkaz:
http://arxiv.org/abs/2406.04496
Many mathematical models have been leveraged to design embeddings for representing Knowledge Graph (KG) entities and relations for link prediction and many downstream tasks. These mathematically-inspired models are not only highly scalable for infere
Externí odkaz:
http://arxiv.org/abs/2309.12501
Knowledge graph entity typing (KGET) is a task to predict the missing entity types in knowledge graphs (KG). Previously, KG embedding (KGE) methods tried to solve the KGET task by introducing an auxiliary relation, 'hasType', to model the relationshi
Externí odkaz:
http://arxiv.org/abs/2308.16055
The incorporation of trees on farms can help to improve livelihoods and build resilience among small-holder farmers in developing countries. On-farm trees can help gen- erate additional income from commercial tree harvest as well as contribute signif
Externí odkaz:
http://arxiv.org/abs/2304.13907
The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE
Externí odkaz:
http://arxiv.org/abs/2304.00378
Knowledge graph completion (KGC) aims to discover missing relationships between entities in knowledge graphs (KGs). Most prior KGC work focuses on learning embeddings for entities and relations through a simple scoring function. Yet, a higher-dimensi
Externí odkaz:
http://arxiv.org/abs/2208.09137
Translation, rotation, and scaling are three commonly used geometric manipulation operations in image processing. Besides, some of them are successfully used in developing effective knowledge graph embedding (KGE) models such as TransE and RotatE. In
Externí odkaz:
http://arxiv.org/abs/2207.05324
Autor:
Ge, Xiou, Goodwin, Richard T., Yu, Haizi, Romero, Pablo, Abdelrahman, Omar, Sudhalkar, Amruta, Kusuma, Julius, Cialdella, Ryan, Garg, Nishant, Varshney, Lav R.
Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other polluta
Externí odkaz:
http://arxiv.org/abs/2204.05397
Publikováno v:
Pattern Recognit. Lett. 157 (2022) 97-103
Entity type prediction is an important problem in knowledge graph (KG) research. A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work. The proposed CORE method leverages the expressive
Externí odkaz:
http://arxiv.org/abs/2112.10067
Publikováno v:
Pattern Recognition Letters, 2022
Knowledge base completion is formulated as a binary classification problem in this work, where an XGBoost binary classifier is trained for each relation using relevant links in knowledge graphs (KGs). The new method, named KGBoost, adopts a modulariz
Externí odkaz:
http://arxiv.org/abs/2112.09340