Filters








3,574 Hits in 3.1 sec

Cross-Language Opinion Lexicon Extraction Using Mutual-Reinforcement Label Propagation

Zheng Lin, Songbo Tan, Yue Liu, Xueqi Cheng, Xueke Xu, Enrique Hernandez-Lemus
2013 PLoS ONE  
To solve the above problems, we explore a mutual-reinforcement label propagation framework.  ...  First, for each language, a label propagation algorithm is applied to a word relation graph, and then a bilingual dictionary is used as a bridge to transfer information between two languages.  ...  The mutual-reinforcement label propagation model is based on bootstrapping.  ... 
doi:10.1371/journal.pone.0079294 pmid:24260190 pmcid:PMC3829905 fatcat:5vyqgiopavdetdt4igffui3dbq

Self-supervised Graph Representation Learning via Bootstrapping [article]

Feihu Che, Guohua Yang, Dawei Zhang, Jianhua Tao, Pengpeng Shao, Tong Liu
2020 arXiv   pre-print
To address these issues, we propose a new self-supervised graph representation method: deep graph bootstrapping~(DGB).  ...  Graph neural networks~(GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning.  ...  Predictions of Bootstrapped Latents(PBL) [26] apply bootstrapping methods to multitask reinforcement learning.  ... 
arXiv:2011.05126v2 fatcat:njifxlwc55dalofk5byo7darsi

Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion [article]

Lingyong Yan, Xianpei Han, Le Sun
2021 arXiv   pre-print
By iteratively performing the above adversarial learning, the generator and the discriminators can reinforce each other and be progressively refined along the whole bootstrapping process.  ...  Conventional bootstrapping methods mostly define the expansion boundary using seed-based distance metrics, which heavily depend on the quality of selected seeds and are hard to be adjusted due to the extremely  ...  Based on the above bipartite graph, each GNN layer aggregates information from node neighbors as follows: v l i = σ(f (W l v l−1 i , j∈N (i) a l i,j W l v l−1 j )) (1) where v l i is node i's embedding  ... 
arXiv:2109.12082v1 fatcat:inuocx3sqrfkddv3lmtwv4jmuq

Robust Conditional Independence maps of single-voxel Magnetic Resonance Spectra to elucidate associations between brain tumours and metabolites

Raúl Vicente Casaña-Eslava, Sandra Ortega-Martorell, Paulo J. Lisboa, Ana Paula Candiota, Margarida Julià-Sapé, José David Martín-Guerrero, Ian H. Jarman, Bryan C Daniels
2020 PLoS ONE  
The obtained results show that ordering nodes by strength of mutual information can recover a representative DAG in a reasonable time, although a more accurate graph can be recovered using a random order  ...  The data set is bootstrapped in order to maximise the robustness of feature selection for nominated target variables.  ...  This node order is based on the averaged mutual information between the node and the rest of nodes by pairs.  ... 
doi:10.1371/journal.pone.0235057 pmid:32609725 fatcat:kxkupkaqxneutbuglietrqemuu

Modeling learning and strategy formation as phase transitions in cortical networks

Robert Kozma, Yury Sokolov, Marko Puljic, Sanquing Hu, Miklos Ruszinko
2016 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)  
On this graph, we consider bootstrap percolation with excitatory and inhibitory vertices. Theoretical and numerical studies indicate the presence of various dynamical regimes on these graphs.  ...  In this work, learning is modeled using a graph-theoretical model, which captures salient characteristics of the learning process.  ...  Based on the analysis of the above Markov process, it can be summarized as follows: Theorem 1: In the mean-field approximation of the bootstrap percolation wtih one type of vertices on the random graph  ... 
doi:10.1109/smc.2016.7844874 dblp:conf/smc/KozmaSPHR16 fatcat:ackf5i4e3rdzzh334egeuj7f4u

Extracting Opinion Targets and Opinion Words from Online Reviews with Graph Co-ranking

Kang Liu, Liheng Xu, Jun Zhao
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
This paper proposes a novel approach to collectively extract them with graph coranking.  ...  First, compared to previous methods which solely employed opinion relations among words, our method constructs a heterogeneous graph to model two types of relations, including semantic relations and opinion  ...  It demonstrates that our graph co-ranking is more suitable for this task than bootstrapping-based strategy.  ... 
doi:10.3115/v1/p14-1030 dblp:conf/acl/LiuXZ14 fatcat:sr5vsghb3nbbxh5gxltpx7ww44

European government bond dynamics and stability policies: taming contagion risks

Peter Schwendner, Martin Schuele, Thomas Ott, Martin Hillebrand
2015 The Journal of Network Theory in Finance  
Using noise-filtered partial correlation influences, this time dependency can be evaluated and visualized using network graphs.  ...  The graphs show both reinforcing and shearing inuences as the Euro area sovereign crisis develops.  ...  They could instead simply be seen as a statistical measure for the mutually reinforcing or shearing inuences of correlations between bond yield changes that happen at the same time.  ... 
doi:10.21314/jntf.2015.012 fatcat:nbxo4ene55abrkvxf2amiydnh4

A measure of the local connectivity between graph vertices

Jie Chen, Ilya Safro
2011 Procedia Computer Science  
We show convergence properties of the proposed measure, and provide a mutually reinforcing model to explain why the algebraic distances meaningfully measure the connectivity in a local sense.  ...  Measuring the connectivity strength between a pair of vertices in a graph is one of the most vital concerns in numerous computational graph problems.  ...  Consider a mutually reinforcing environment, where entities are influenced by their neighbors.  ... 
doi:10.1016/j.procs.2011.04.021 fatcat:ddvrq3zhavbstdhn6qqeubhdwy

A Measure of the Connection Strengths between Graph Vertices with Applications [article]

Jie Chen, Ilya Safro
2009 arXiv   pre-print
Based on an analysis of the convergence property, we propose a mutually reinforcing model to explain the intuition behind the strategy.  ...  We present a simple iterative strategy for measuring the connection strength between a pair of vertices in a graph.  ...  Mutually Reinforcing Model The local structure of a graph and the edge weights are two factors that mutually govern the strength of the connection between a pair of vertices.  ... 
arXiv:0909.4275v1 fatcat:bnpyl5dcd5earjkpbpuz72xsd4

Collective Corpus Weighting and Phrase Scoring for SMT Using Graph-Based Random Walk [chapter]

Lei Cui, Dongdong Zhang, Shujie Liu, Mu Li, Ming Zhou
2013 Communications in Computer and Information Science  
The method uses the mutual reinforcement between the sentence pairs and the extracted phrase pairs, based on the observation that better sentence pairs often lead to better phrase extraction and vice versa  ...  An effective graph-based random walk is designed to estimate the quality of sentence pairs and phrase pairs simultaneously.  ...  This kind of mutual reinforcement fits well into the framework of graph-based random walk. When a phrase pair p is extracted from a sentence pair s, s is considered casting a vote for p.  ... 
doi:10.1007/978-3-642-41644-6_17 fatcat:d3qtmj5rw5acne6okeuaghukou

Using an Agent-Based Model to Simulate the Development of Risk Behaviors During Adolescence

Nils Schuhmacher, Laura Ballato, Paul van Geert
2014 Journal of Artificial Societies and Social Simulation  
Using an agent-based model to simulate the development of risk behaviors during adolescence Schuhmacher, N.; Ballato, Laura; van Geert, Paul  ...  The graph is a visualization of the mutuality matrix made with Netdraw (Borgatti 2002) . A friendship connection indicates a mutuality value > 0.8.  ...  Friendship clustering is based on a dissimilarity matrix (which is calculated on the basis of the mutuality matrix at t = 2000).  ... 
doi:10.18564/jasss.2485 fatcat:ic75pqahrfe5xloisrkoszgp6e

Mechanistic insights into mutually exclusive splicing in dynamin 1

Mikita Suyama
2013 Computer applications in the biosciences : CABIOS  
Mutually exclusive splicing is a strictly regulated pattern of alternative splicing.  ...  A specific group of mutually exclusive splicing events has been shown to be regulated by the formation of specific RNA secondary structures.  ...  The numbers at the internal nodes indicate bootstrap values based on 100 replicates.  ... 
doi:10.1093/bioinformatics/btt368 pmid:23793749 fatcat:6zkqrcqt5zdrzciyq7sszivlm4

Deep Reinforcement Learning for Entity Alignment [article]

Lingbing Guo and Yuqiang Han and Qiang Zhang and Huajun Chen
2022 arXiv   pre-print
The proposed reinforcement learning (RL)-based entity alignment framework can be flexibly adapted to most embedding-based EA methods.  ...  The most notable is that they identify the aligned entities based on cosine similarity, ignoring the semantics underlying the embeddings themselves.  ...  Deep Reinforcement Learning for Knowledge Graphs One most relevant work to this paper is CEAFF (Zeng et al., 2021) , which also leverages RL algorithms and believes in 1-to-1 alignment.  ... 
arXiv:2203.03315v1 fatcat:a5yoap6x4vbpjb4sxqushudyo4

Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification [article]

Sung Hwan Mun, Min Hyun Han, Dongjune Lee, Jihwan Kim, Nam Soo Kim
2021 arXiv   pre-print
Experimental results show that the proposed bootstrap equilibrium training strategy can effectively help learn the speaker representations and outperforms the conventional methods based on contrastive  ...  In the back-end stage, the probabilistic speaker embeddings are estimated by maximizing the mutual likelihood score between the speech samples belonging to the same speaker, which provide not only speaker  ...  “Self-supervised graph representation learning via bootstrap- Seoul, Korea, in 2018.  ... 
arXiv:2112.08929v1 fatcat:cm4plnaw2ngtnk23s5pq3cmjhe

Learning to query: Focused web page harvesting for entity aspects

Yuan Fang, Vincent W. Zheng, Kevin Chen-Chuan Chang
2016 2016 IEEE 32nd International Conference on Data Engineering (ICDE)  
Such mutual reinforcement can be modeled by a reinforcement graph G = (V, E), as illustrated in Fig. 2 (c).  ...  Interestingly, these definitions apply uniformly to pages and queries, enabling us to capture their mutual reinforcement in a unified way. Mutual reinforcement.  ... 
doi:10.1109/icde.2016.7498308 dblp:conf/icde/FangZC16 fatcat:maz64huqrjc6daxp7ivnknb534
« Previous Showing results 1 — 15 out of 3,574 results