42,388 Hits in 4.9 sec

Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs [article]

Houyu Zhang, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu
2020 arXiv   pre-print
The traverse is guided by graph attentions in the concept graph, moving towards more meaningful directions in the concept space, in order to generate more semantic and informative responses.  ...  This paper presents a new conversation generation model, ConceptFlow, which leverages commonsense knowledge graphs to explicitly model conversation flows.  ...  Then ConceptFlow encodes both central and outer concept flows in central graph G central and outer graph G outer , using graph neural networks and concept embedding (Sec. 3.3).  ... 
arXiv:1911.02707v3 fatcat:fxjuyllabfgmbn7baxtc4fz7dm

KATRec: Knowledge Aware aTtentive Sequential Recommendations [article]

Mehrnaz Amjadi, Seyed Danial Mohseni Taheri, Theja Tulabandhula
2021 arXiv   pre-print
To address this, we present a solution enhanced by a knowledge graph called KATRec (Knowledge Aware aTtentive sequential Recommendations).  ...  KATRec learns the short and long-term interests of users by modeling their sequence of interacted items and leveraging pre-existing side information through a knowledge graph attention network.  ...  First, we learn the initial item embeddings using the knowledge graph attention module.  ... 
arXiv:2012.03323v3 fatcat:do5irumjsnegzair4fdn25aggq

SAKG-BERT: Enabling Language Representation With Knowledge Graphs for Chinese Sentiment Analysis

Xiaoyan Yan, Fanghong Jian, Bo Sun
2021 IEEE Access  
Knowledge graphs can enhance language representation. Furthermore, knowledge graphs have high entity / concept coverage and strong semantic expression ability.  ...  We propose a sentiment analysis knowledge graph (SAKG)-BERT model that combines sentiment analysis knowledge and the language representation model BERT.  ...  ACKNOWLEDGMENT Xiaoyan Yan would like to thank her Ph.D. supervisor Prof. Jimmy Huang for his advice and encouragement during the preparation of this article.  ... 
doi:10.1109/access.2021.3098180 fatcat:hof5rwm7w5eopkehpawvnxcflu

Personalized News Recommendation: A Survey [article]

Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Xing Xie
2021 arXiv   pre-print
This paper can provide up-to-date and comprehensive views to help readers understand the personalized news recommendation field.  ...  However, there are still many unsolved problems and challenges that need to be further studied.  ...  KRED [99] first learns entity embeddings from knowledge graph with graph attention networks, then incorporates additional entity features such as frequency, category and position, and finally selects  ... 
arXiv:2106.08934v2 fatcat:mpbs3vr75ncw7npnp5uhwj5v4e

A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations

Dehai Zhang, Xiaobo Yang, Linan Liu, Qing Liu
2021 Applied Sciences  
The second is the knowledge graph-embedded model, which aims to integrate the knowledge. The semantic information of the nodes and edges in the graph is mapped to the low-dimensional vector space.  ...  This is an end-to-end deep learning model using knowledge graph embedding to enhance the attention aggregation network for making recommendations. It consists of three main parts.  ...  Knowledge Graph Embedding The function of knowledge graph embedding is to embed the entity and relationship in the knowledge graph into a continuous low-dimensional vector space to facilitate the sharing  ... 
doi:10.3390/app112110432 fatcat:npw7ilnoefh4zgwccbddh4lfdy

When Radiology Report Generation Meets Knowledge Graph

Yixiao Zhang, Xiaosong Wang, Ziyue Xu, Qihang Yu, Alan Yuille, Daguang Xu
The incorporation of knowledge graph allows for dedicated feature learning for each disease finding and the relationship modeling between them.  ...  Based on these concerns, we propose to utilize a pre-constructed graph embedding module (modeled with a graph convolutional neural network) on multiple disease findings to assist the generation of reports  ...  Attention mechanism and graph convolution are adapted to learn the graph embedded features.  ... 
doi:10.1609/aaai.v34i07.6989 fatcat:u63mv6sh2jfgtnqkjyz45dpvsu

When Radiology Report Generation Meets Knowledge Graph [article]

Yixiao Zhang, Xiaosong Wang, Ziyue Xu, Qihang Yu, Alan Yuille, Daguang Xu
2020 arXiv   pre-print
The incorporation of knowledge graph allows for dedicated feature learning for each disease finding and the relationship modeling between them.  ...  Based on these concerns, we propose to utilize a pre-constructed graph embedding module (modeled with a graph convolutional neural network) on multiple disease findings to assist the generation of reports  ...  Attention mechanism and graph convolu-tion are adapted to learn the graph embedded features.  ... 
arXiv:2002.08277v1 fatcat:h5jlecgt2rcczjkpodykkvijlq

Integrating Graph Contextualized Knowledge into Pre-trained Language Models [article]

Bin He, Di Zhou, Jinghui Xiao, Xin jiang, Qun Liu, Nicholas Jing Yuan, Tong Xu
2021 arXiv   pre-print
to learn the knowledge embeddings.  ...  Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information.  ...  Graph attention networks (GATs) (Veličković et al. 2018 ) update the entity embedding by its 1-hop neighbors, which pays more attention to the node information interactions.  ... 
arXiv:1912.00147v3 fatcat:7ovn5wag2nb4vpjhz6hjnyysla

Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation [article]

Gaode Chen, Xinghua Zhang, Yanyan Zhao, Cong Xue, Ji Xiang
2021 arXiv   pre-print
Meanwhile, an ingenious graph is proposed to enhance the interactivity between items in user's behavior sequence, which can capture both global and local item features.  ...  Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in the literature.  ...  Acknowledgments This work is supported by National Key Research and Development Program of China.  ... 
arXiv:2106.04415v1 fatcat:iia3i7lalzgiraxqtjqc4elg6u

ATPGNN: Reconstruction of Neighborhood in Graph Neural Networks with Attention-based Topological Patterns

Kehao Wang, Hantao Qian, Xuming Zeng, Mozi Chen, Kezhong Liu, Kai Zheng, Pan Zhou, Dapeng Wu
2021 IEEE Access  
Finally, we combine the representation information of remote nodes, graph structure information and feature for each node by attention mechanism, and apply them to learning node representation in graph  ...  Third, we use some network embedding methods to get graph structure information of each node.  ...  product recommendation and semantic search in knowledge graphs [13] , [14] .  ... 
doi:10.1109/access.2021.3050541 fatcat:pn5uyqnvr5dw3ord6hhytzlgqm

Multi-source knowledge fusion: a survey

Xiaojuan Zhao, Yan Jia, Aiping Li, Rong Jiang, Yichen Song
2020 World wide web (Bussum)  
promote the construction of domain knowledge graphs (KGs), and bring enormous social and economic benefits.  ...  Due to the uncertainty of knowledge acquisition, the reliability and confidence of KG based on entity recognition and relationship extraction technology need to be evaluated.  ...  as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.  ... 
doi:10.1007/s11280-020-00811-0 fatcat:ef5j2sna6fai7k2455yihrrfuq

COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human  ...  commonsense knowledge graphs.  ...  Acknowledgments We thank Thomas Wolf, Ari Holtzman, Chandra Bhagavatula, Peter Clark, Rob Dalton, Ronan Le Bras, Rowan Zellers and Scott Yih for helpful discussions over the course of this project, as  ... 
doi:10.18653/v1/p19-1470 dblp:conf/acl/BosselutRSMCC19 fatcat:xosmwkdenrerxk7i2sxx43k7aq

Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts [article]

Faisal Alshargi, Saeedeh Shekarpour, Tommaso Soru, Amit Sheth
2020 arXiv   pre-print
Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models.  ...  We positioned our sampled data and code at under GNU General Public License v3.0.  ...  The quality of embeddings is attributed to the true reflection of semantics and structural patterns of the knowledge graph in an embedding space.  ... 
arXiv:1803.04488v3 fatcat:jpupzhl3srdr7oghywvysrf6qa

Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering [article]

Zhuoqian Yang, Zengchang Qin, Jing Yu, Yue Hu
2019 arXiv   pre-print
To fully capture visual semantics, we propose to reason over a structured visual representation - scene graph, with embedded objects and inter-object relationships.  ...  Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer.  ...  [10] introduces language based and embedding based supervision to cope with the long-tailed distribution of training data, which used to undermine the quality of label-based supervision.  ... 
arXiv:1812.09681v2 fatcat:aataimf5n5btbnfkl4fsyvl3we

Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization [article]

Beliz Gunel, Chenguang Zhu, Michael Zeng, Xuedong Huang
2020 arXiv   pre-print
First, we incorporate entity-level knowledge from the Wikidata knowledge graph into the encoder-decoder architecture.  ...  However, these models have two critical shortcomings: they often don't respect the facts that are either included in the source article or are known to humans as commonsense knowledge, and they don't produce  ...  Wikidata Knowledge Graph Entity Embeddings Wikidata is a free and open multi-relational knowledge graph that serves as the central storage for the structured data of its many services including Wikipedia  ... 
arXiv:2006.15435v1 fatcat:3vqktozonjfwdowyvawrqm4vkq
« Previous Showing results 1 — 15 out of 42,388 results