78,437 Hits in 4.8 sec

Term-specific eigenvector-centrality in multi-relation networks

François Bry, Fabian Kneissl, Klara Weiand, Tim Furche
2012 International Journal of Social Network Mining  
Fuzzy matching and ranking are two information retrieval techniques widely used in web search. Their application to structured data, however, remains an open problem.  ...  This article investigates how eigenvector-centrality can be used for approximate matching in multirelation graphs, that is, graphs where connections of many dierent types may exist.  ...  Consequently, the approach presented in this article can accommodate rich graphs that represent, for example, both hypertext linking as well as semantic and social relationships.  ... 
doi:10.1504/ijsnm.2012.051055 fatcat:tbkipi7r3jhtplpetiic2aarlq

Multi-Modal Retrieval using Graph Neural Networks [article]

Aashish Kumar Misraa, Ajinkya Kale, Pranav Aggarwal, Ali Aminian
2020 arXiv   pre-print
We model the visual and concept relationships as a graph structure, which captures the rich information through node neighborhood.  ...  This graph structure helps us learn multi-modal node embeddings using Graph Neural Networks.  ...  We model the visual and attribute relationships as a graph structure, which is able to capture the rich information through node neighborhood.  ... 
arXiv:2010.01666v1 fatcat:mtp43eajpbabnhownf6tqaxhki

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
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  ...  Therefore, the research on mining and searching the association relationship of scientific papers based on deep learning has far-reaching practical significance.  ...  Rich semantic relationships in structured data, and mining the features and associations between nodes in the graph.  ... 
arXiv:2204.11488v1 fatcat:zxwvpnids5bopberzumjofgupq

T-Know: a Knowledge Graph-based Question Answering and Infor-mation Retrieval System for Traditional Chinese Medicine

Ziqing Liu, Enwei Peng, Shixing Yan, Guozheng Li, Tianyong Hao
2018 International Conference on Computational Linguistics  
In addition, the TCM knowledge graph also is used to support human-computer interactive knowledge retrieval by normalizing search keywords to medical terminology.  ...  T-Know is a knowledge service system based on the constructed knowledge graph of Traditional Chinese Medicine (TCM).  ...  A typical situation is that, their search functions allow formal TCM terms only, causing common users without TCM background difficulties to obtain required information without rich TCM background.  ... 
dblp:conf/coling/LiuPYLH18 fatcat:5y7clf3ls5gkndjprs7taahqye

Visual Exploratory Search of Relationship Graphs on Smartphones

Jianquan Ouyang, Hao Zheng, Fanbin Kong, Tianming Liu, Michael J Proulx
2013 PLoS ONE  
rich information world of interlinked relationship graphs in a personalized fashion; 3) it effectively takes the advantages of smartphones' user-friendly interfaces and ubiquitous Internet connection and  ...  graphs on the Web via meta-search, visual exploratory search of relationship graphs through both querying and browsing strategies, and human-computer interactions via the multi-touch interface and mobile  ...  in a rich information world.  ... 
doi:10.1371/journal.pone.0079379 pmid:24223936 pmcid:PMC3817041 fatcat:7gt66na62bcpppjwanexe3v6pq

MARiO: Multi-Attribute Routing in Open Street Map [chapter]

Franz Graf, Hans-Peter Kriegel, Matthias Renz, Matthias Schubert
2011 Lecture Notes in Computer Science  
In recent years, the Open Street Map (OSM) project collected a large repository of spatial network data containing a rich variety of information about traffic lights, road types, points of interest etc  ...  Formally, this network can be described as a multi-attribute graph, i.e. a graph considering multiple attributes when describing the traversal of an edge.  ...  For example, we have information about traffic lights and altitudes connected to the nodes which have to be reassigned and post processed into edge attributes of a multi-attribute graph.  ... 
doi:10.1007/978-3-642-22922-0_36 fatcat:7x6bta3p6fdurmygz7mni2e734

UDBMS: Road to Unification for Multi-model Data Management [article]

Jiaheng Lu, Zhen Hua Liu, Pengfei Xu, Chao Zhang
2016 arXiv   pre-print
For example, semi-structured, graph and relational models are examples of data models that may be supported by a new system.  ...  In this paper, we envision a UDBMS (Unified Database Management System) for multi-model data management in one platform.  ...  Assuming that users' information is stored in JSON documents, while friend relationships are stored in a graph.  ... 
arXiv:1612.08050v1 fatcat:7qek5sljnrbjvhuwpfsh4duj5y

DiseaseAtlas: Multi-facet visual analytics for online disease articles

Jimeng Sun, D Gotz, Nan Cao
2010 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology  
Online health information portals provide valuable content to casual consumers.  ...  We have developed a visual analytic system named DiseaseAtlas that helps users navigate a large set of disease-related documents and understand multi-dimensional relationships for key semantic concepts  ...  DISEASEATLAS VISUALIZATION DiseaseAtlas combines a background-layer density map with multi-faceted graph-based diagrams rendered in the foreground to display both global cluster information as well as  ... 
doi:10.1109/iembs.2010.5627103 pmid:21096321 fatcat:27kva72y5vgh5bacoxkurvrcci

Reinforcement Learning over Knowledge Graphs for Explainable Dialogue Intent Mining

Kai Yang, Xinyu Kong, Yafang Wang, Jie Zhang, Gerard De Melo
2020 IEEE Access  
For more information, see VOLUME 8, 2020  ...  To address this, we propose a scheme to interpret the intent in multi-turn dialogue based on specific characteristics of the dialogue text.  ...  For example, in terms of question answering, a knowledge graph may be considered as the environment for an agent.  ... 
doi:10.1109/access.2020.2991257 fatcat:wtgscficrzdozp25zy2arysxpi

Extracting words and multi-part symbols in graphics rich documents [chapter]

Mark Burge, Gladys Monagan
1995 Lecture Notes in Computer Science  
Results are presented with example images taken from those used by our Swiss cadastral map understanding system.  ...  No a priori font or other domain specific information is required for the grouping, and no special geometrical relationships among the elements are assumed.  ...  The ambiguity which arises during localization, for example between dashes, ones, and "i'"s is resolved by referring to the neighborhood graph for contextual information.  ... 
doi:10.1007/3-540-60298-4_310 fatcat:lzhh4fp5hbgrpi2nnt5nvrq2py

Intelligent Interaction with Virtual Geographical Environments Based on Geographic Knowledge Graph

Bingchuan Jiang, Liheng Tan, Yan Ren, Feng Li
2019 ISPRS International Journal of Geo-Information  
A geographic knowledge graph (GeoKG) is a large-scale semantic web that stores geographical knowledge in a structured form.  ...  We construct a multi-level semantic parsing model and an enhanced GeoKG for structured geographic information data, such as digital maps, 3D virtual scenes, and unstructured information data.  ...  The knowledge graph (KG) was formally proposed in 2012 by Google to achieve a more intelligent search engine.  ... 
doi:10.3390/ijgi8100428 fatcat:chqinehmzbem7dgeye7ceeqss4

GraphSearchNet: Enhancing GNNs via Capturing Global Dependency for Semantic Code Search [article]

Shangqing Liu, Xiaofei Xie, Jingkai Siow, Lei Ma, Guozhu Meng, Yang Liu
2022 arXiv   pre-print
To address these challenges, in this paper, we design a novel neural network framework, named GraphSearchNet, to enable an effective and accurate source code search by jointly learning rich semantics of  ...  Furthermore, the widely adopted Graph Neural Networks (GNNs) have proved the effectiveness in learning program semantics, however, they also suffer the problem of capturing the global dependency in the  ...  However, these DL-based techniques in code search are mostly based on sequential model and ignore the rich structural information behind the programs and queries.  ... 
arXiv:2111.02671v3 fatcat:lco2syw7ijbh7bfw4bhd53dvbq

Thesaurus-Based Search in Large Heterogeneous Collections [chapter]

Jan Wielemaker, Michiel Hildebrand, Jacco van Ossenbruggen, Guus Schreiber
2008 Lecture Notes in Computer Science  
In this paper we describe the design rationale of ClioPatria, an open-source system which provides APIs for scalable semantic graph search.  ...  We discuss details of scalable graph search, the required OWL reasoning functionalities and show why SPARQL queries are insufficient for solving the search problem. 5 The software can be found at http:  ...  In our current datasets for example, the subgraphs with geographical information are both huge and connected to the rest of the graph in a limited and predictable fashion.  ... 
doi:10.1007/978-3-540-88564-1_44 fatcat:c53pnv7jlvah7nmavktoj7clr4

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy.  ...  Query-based open-domain NLP tasks require information synthesis from long and diverse web results.  ...  search information.  ... 
doi:10.18653/v1/d19-1428 dblp:conf/emnlp/FanGBB19 fatcat:u4uju6ob7rcnvd3mqcavkgc6ey

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs [article]

Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes
2019 arXiv   pre-print
We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy.  ...  For two generative tasks with very long text input, long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved  ...  search information.  ... 
arXiv:1910.08435v1 fatcat:2epldhegyfbsxmqtb5jngtfgra
« Previous Showing results 1 — 15 out of 78,437 results