Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Nayyeri, Mojtaba"'
Autor:
Zhu, Yuqicheng, Potyka, Nico, Xiong, Bo, Tran, Trung-Kien, Nayyeri, Mojtaba, Kharlamov, Evgeny, Staab, Steffen
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a s
Externí odkaz:
http://arxiv.org/abs/2407.11821
Autor:
He, Yunjie, Hernandez, Daniel, Nayyeri, Mojtaba, Xiong, Bo, Zhu, Yuqicheng, Kharlamov, Evgeny, Staab, Steffen
Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily
Externí odkaz:
http://arxiv.org/abs/2407.09212
Large Language Models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize this advanced reasoning with a combi
Externí odkaz:
http://arxiv.org/abs/2402.13602
Temporal knowledge graphs represent temporal facts $(s,p,o,\tau)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $\tau$, where $\tau$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temp
Externí odkaz:
http://arxiv.org/abs/2312.13680
Reasoning with knowledge graphs (KGs) has primarily focused on triple-shaped facts. Recent advancements have been explored to enhance the semantics of these facts by incorporating more potent representations, such as hyper-relational facts. However,
Externí odkaz:
http://arxiv.org/abs/2312.09219
Autor:
Xiong, Bo, Nayyeri, Mojtaba, Jin, Ming, He, Yunjie, Cochez, Michael, Pan, Shirui, Staab, Steffen
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions. Their prese
Externí odkaz:
http://arxiv.org/abs/2304.11949
Answering first-order logical (FOL) queries over knowledge graphs (KG) remains a challenging task mainly due to KG incompleteness. Query embedding approaches this problem by computing the low-dimensional vector representations of entities, relations,
Externí odkaz:
http://arxiv.org/abs/2303.11858
Predicting missing links between entities in a knowledge graph is a fundamental task to deal with the incompleteness of data on the Web. Knowledge graph embeddings map nodes into a vector space to predict new links, scoring them according to geometri
Externí odkaz:
http://arxiv.org/abs/2302.06229
Autor:
Nayyeri, Mojtaba, Wang, Zihao, Akter, Mst. Mahfuja, Alam, Mirza Mohtashim, Rony, Md Rashad Al Hasan, Lehmann, Jens, Staab, Steffen
Knowledge Graphs, such as Wikidata, comprise structural and textual knowledge in order to represent knowledge. For each of the two modalities dedicated approaches for graph embedding and language models learn patterns that allow for predicting novel
Externí odkaz:
http://arxiv.org/abs/2208.02743
Autor:
Xiong, Bo, Zhu, Shichao, Nayyeri, Mojtaba, Xu, Chengjin, Pan, Shirui, Zhou, Chuan, Staab, Steffen
Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneous, i.e., a KG is composed of m
Externí odkaz:
http://arxiv.org/abs/2206.00449