Filters








66,315 Hits in 3.5 sec

Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings [article]

Guanglin Niu, Yang Li, Chengguang Tang, Zhongkai Hu, Shibin Yang, Peng Li, Chengyu Wang, Hao Wang, Jian Sun
2021 arXiv   pre-print
Recent approaches attempt to introduce the knowledge graph embedding (KGE) technique to handle the KG incompleteness but only consider the triple facts and neglect the significant semantic correlation  ...  In this paper, we propose a Path and Knowledge Embedding-Enhanced multi-relational Question Answering model (PKEEQA), which leverages multi-hop paths between entities in the KG to evaluate the ambipolar  ...  Inspired by the KG embedding technique for KG completion, EmbedKGQA (Saxena et al., 2020) employs the pre-trained entity embeddings by KGE and the question embedding to calculate the score of each candidate  ... 
arXiv:2110.15622v1 fatcat:vghuvwptlnfntoyb7zpu56ia2i

RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion [article]

Youri Xu, E Haihong, Meina Song, Wenyu Song, Xiaodong Lv, Wang Haotian, Yang Jinrui
2021 arXiv   pre-print
Static knowledge graph (SKG) embedding (SKGE) has been studied intensively in the past years. Recently, temporal knowledge graph (TKG) embedding (TKGE) has emerged.  ...  In this paper, we propose a Recursive Temporal Fact Embedding (RTFE) framework to transplant SKGE models to TKGs and to enhance the performance of existing TKGE models for TKG completion.  ...  Acknowledgements This work was supported in part by the National Science Foundation of China (Grant No. 61902034); Engineering Research Center of Information Networks, Ministry of Education.  ... 
arXiv:2009.14653v4 fatcat:63torcfukrhibif2w3fvbftece

QuatRE: Relation-Aware Quaternions for Knowledge Graph Embeddings [article]

Dai Quoc Nguyen and Thanh Vu and Tu Dinh Nguyen and Dinh Phung
2022 arXiv   pre-print
We propose a simple yet effective embedding model to learn quaternion embeddings for entities and relations in knowledge graphs.  ...  Experimental results show that our proposed model produces state-of-the-art performances on well-known benchmark datasets for knowledge graph completion. Our code is available at: .  ...  However, these two variants of QuatRE still outperforms QuatE, hence clearly showing the advantage of further using the relation-aware rotations in our QuatRE to enhance the correlations in knowledge graphs  ... 
arXiv:2009.12517v2 fatcat:alpth2t7cvhepibmqnrgddlpme

KnowAugNet: Multi-Source Medical Knowledge Augmented Medication Prediction Network with Multi-Level Graph Contrastive Learning [article]

Yang An, Bo Jin, Xiaopeng Wei
2022 arXiv   pre-print
ontology graph and obtains the knowledge augmented medical codes embedding vectors.  ...  Then, it utilizes the graph contrastive learning using a weighted graph convolutional network as the encoder to capture the correlative relations between homogeneous or heterogeneous medical codes from  ...  Acknowledgements Funding: This research was partially supported by the National Key R&D Program of China (2018YFC0116800), National Natural Science Foundation of China (No. 61772110, 6217072188 and 71901011  ... 
arXiv:2204.11736v2 fatcat:vvncqo2tejgwrbpo2cxpstqdt4

Unifying Task-oriented Knowledge Graph Learning and Recommendation

Qianyu Li, Xiaoli Tang, Tengyun Wang, Haizhi Yang, Hengjie Song
2019 IEEE Access  
The RCoLM aims at transferring knowledge between recommendation task and knowledge graph completion (KG completion) task by utilizing a transfer learning model.  ...  from recommendations for KG completion, and unifies the two tasks in a joint model for mutual enhancements.  ...  Due to negative sampling triples of relation, RCoLM can utilize and maintain the structural information in the knowledge graph more comprehensively, and it further enhances the performance of the embedding  ... 
doi:10.1109/access.2019.2932466 fatcat:wvlchwdaynblbfymecyt5p3m7y

Leveraging Concept-Enhanced Pre-Training Model and Masked-Entity Language Model for Named Entity Disambiguation

Zizheng Ji, Lin Dai, Jin Pang, Tingting Shen
2020 IEEE Access  
Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in an input-text sequence to their correct references in a knowledge graph.  ...  Therefore, the proposed pre-training NED model could merge the advantage of pre-training mechanism for generating contextualized embedding with the superiority of the lexical knowledge (e.g., concept knowledge  ...  graph completion [13] , [14] , [23] , [45] .  ... 
doi:10.1109/access.2020.2994247 fatcat:m5e2h3w5gnat3imgre6e5swx5e

Association Rules Enhanced Knowledge Graph Attention Network [article]

Zhenghao Zhang, Jianbin Huang, Qinglin Tan
2020 arXiv   pre-print
Most existing knowledge graphs suffer from incompleteness. Embedding knowledge graphs into continuous vector spaces has recently attracted increasing interest in knowledge base completion.  ...  To overcome the problem, we propose an association rules enhanced knowledge graph attention network (AR-KGAT).  ...  ACKNOWLEDGMENTS The work was supported by the National Natural Science Foundation of China [grant numbers: 61876138, 61602354].  ... 
arXiv:2011.08431v1 fatcat:l6sfja6ycng7bkszyclgih5qiu

Learning Rare Word Representations using Semantic Bridging [article]

Victor Prokhorov, Mohammad Taher Pilehvar, Dimitri Kartsaklis, Pietro Lió, Nigel Collier
2017 arXiv   pre-print
Squares and Canonical Correlation Analysis) in order to merge the corpus and ontological sources of lexical knowledge.  ...  We propose a methodology that adapts graph embedding techniques (DeepWalk (Perozzi et al., 2014) and node2vec (Grover and Leskovec, 2016)) as well as cross-lingual vector space mapping approaches (Least  ...  Acknowledgments This research was supported by EPSRC Experienced Researcher Fellowship (Nigel Collier, Dimitri Kartsaklis, (EP/M005089/1)), MRC grant (Mohammad Taher Pilehvar, (MR/M025160/1)) We gratefully  ... 
arXiv:1707.07554v1 fatcat:pwhyz3z6kzfutjavty7auszc3u

A Model of Text-Enhanced Knowledge Graph Representation Learning with Mutual Attention

Yashen Wang, Huanhuan Zhang, Ge Shi, Zhirun Liu, Qiang Zhou
2020 IEEE Access  
Recently, it has gained lots of interests to jointly learn the embeddings of knowledge graph (KG) and text information.  ...  This paper proposes a novel text-enhanced knowledge graph representation model, which can utilize textual information to enhance the knowledge representations.  ...  EXPERIMENTS We evaluate our proposed text-enhanced knowledge graph representation model with mutual attention based on Knowledge Graph Completion (KGC) task, mainly consists of: Link Prediction (Section  ... 
doi:10.1109/access.2020.2981212 fatcat:6uhn2qkedjcqrln3hd6xdy2zbq

Semantically Enhanced Models for Commonsense Knowledge Acquisition [article]

Ikhlas Alhussien, Erik Cambria, Zhang NengSheng
2018 arXiv   pre-print
The proposed models enhance in a knowledge graph embedding (KGE) framework for knowledge base completion.  ...  To address these challenges, this paper presents semantically enhanced models to enable reasoning through resolving part of commonsense ambiguity.  ...  We use semantically enhanced embeddings to perform knowledge base completion (KBC), a technique that perform reasoning over existing knowledge in supervised manner to predict missing assertions by filling  ... 
arXiv:1809.04708v2 fatcat:mzvmg56c5bchtltayiwsgk3lki

Scientific and Technological Resource Sharing Model Based on Few-Shot Relational Learning

Yangshengyan LIU, Fu GU, Yangjian JI, Yijie WU, Jianfeng GUO, Xinjian GU, Jin ZHANG
2021 IEICE transactions on information and systems  
Here we propose a novel method to share scientific and technological resources by storing resources as nodes and correlations as links to form a complex network.  ...  We also show two practical applications, a resource graph and a resource map, to demonstrate how the complex network helps resource sharing.  ...  the original knowledge is kept and enhanced.  ... 
doi:10.1587/transinf.2020bdp0021 fatcat:caoeiwdfmjawfb6din5zurhao4

Enhancing Semantic Word Representations by Embedding Deeper Word Relationships [article]

Anupiya Nugaliyadde, Kok Wai Wong, Ferdous Sohel, Hong Xie
2019 arXiv   pre-print
Embedding deeper word relationships which are not represented in the context enhances the word representation.  ...  The proposed word representation shows a Spearman correlation score of 0.886 and provided the best results when compared to the current state-of-the-art methods, and exceed the human performance of 0.78  ...  The semantic and knowledge-graph embedding are combined to create one-word embedding, representing both a semantic and general word representation.  ... 
arXiv:1901.07176v1 fatcat:l2vcvimvu5ctrasqtxncfd3nre

Transformer-Empowered Content-Aware Collaborative Filtering [article]

Weizhe Lin, Linjun Shou, Ming Gong, Pei Jian, Zhilin Wang, Bill Byrne, Daxin Jiang
2022 arXiv   pre-print
Knowledge graph (KG) based Collaborative Filtering is an effective approach to personalizing recommendation systems for relatively static domains such as movies and books, by leveraging structured information  ...  of knowledge-graph-based collaborative filtering systems to exploit item content information.  ...  For example, KTUP [2] jointly trained KG completion and item recommendation simultaneously with item embeddings enhanced by TransH-powered KG completion.  ... 
arXiv:2204.00849v1 fatcat:haphrtxrezah7kogkgupceik6q

FoodKG: A Tool to Enrich Knowledge Graphs Using Machine Learning Techniques

Mohamed Gharibi, Arun Zachariah, Praveen Rao
2020 Frontiers in Big Data  
FoodKG employs an existing graph embedding technique trained on a controlled vocabulary called AGROVOC, which is published by the Food and Agriculture Organization of the United Nations.  ...  The resulting model obtained after training on AGROVOC was evaluated against the state-of-the-art word embedding and knowledge graph embedding models that were trained on the same dataset.  ...  This work was supported in part by the National Science Foundation under grant No. 1747751. Part of this work was done when the second and third authors were at the University of Missouri-Kansas City.  ... 
doi:10.3389/fdata.2020.00012 pmid:33693387 pmcid:PMC7931944 fatcat:3vaonvpuabhinhgdn5ehmvvt5u

Mining and searching association relation of scientific papers based on deep learning [article]

Jie Song and Meiyu Liang and Zhe Xue and Feifei Kou and Ang Li
2022 arXiv   pre-print
There is a complex correlation among the data of scientific papers.  ...  The phenomenon reveals the data characteristics, laws, and correlations contained in the data of scientific and technological papers in specific fields, which can realize the analysis of scientific and  ...  [76] proposed the InteractE method to enhance features in knowledge graphs correlation between the vectors and achieved the best results.  ... 
arXiv:2204.11488v1 fatcat:zxwvpnids5bopberzumjofgupq
« Previous Showing results 1 — 15 out of 66,315 results