24,986 Hits in 4.8 sec

(Partial) user preference similarity as classification-based model similarity

Amancio Bouza, Abraham Bernstein
2014 Semantic Web Journal  
Furthermore, the concept of partial preference similarity based on a machine learning model is presented.  ...  Furthermore, the concept of partial preference similarity based on a machine learning model is presented.  ...  Additionally, the F 1 -score is computed, which accounts for the well-known trade-off between P recision and Recall.  ... 
doi:10.3233/sw-130099 fatcat:2qyi243ctfb2tk6mo6d3nbn7qe

Assessing MCR Discussion Usefulness Using Semantic Similarity

Thai Pangsakulyanont, Patanamon Thongtanunam, Daniel Port, Hajimu Iida
2014 2014 6th International Workshop on Empirical Software Engineering in Practice  
We propose to utilize semantic similarity as a practical, costefficient, and empirically assurable approach for assisting with the manual usefulness assessment of MCR comments.  ...  Recent studies indicate there is a positive relationship between the number of review comments and code quality.  ...  We find these thresholds by selecting s t , d t values that maximize the F-measure [6] , [7] which is a performance measure for a binary classification that compromises trade-offs in accuracy of classification  ... 
doi:10.1109/iwesep.2014.11 dblp:conf/iwesep/Pangsakulyanont14 fatcat:qhqggw53e5cvbadztpoqqsd5cm

Evaluating similarity measures for emergent semantics of social tagging

Benjamin Markines, Ciro Cattuto, Filippo Menczer, Dominik Benz, Andreas Hotho, Gerd Stumme
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory.  ...  The results are consistent across resource and tag similarity.  ...  Acknowledgments We are grateful to Heather Roinestad for the ODP similarity network, Mark Meiss for his implementation of Kendall's τ , and Luis Rocha for helpful comments on fuzzy notions of joint probability  ... 
doi:10.1145/1526709.1526796 dblp:conf/www/MarkinesCMBHS09 fatcat:g7jq3yidhbe7lnr2ffeprqchqq

Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO [article]

Zarana Parekh, Jason Baldridge, Daniel Cer, Austin Waters, Yinfei Yang
2021 arXiv   pre-print
We address this gap with Crisscrossed Captions (CxC), an extension of the MS-COCO dataset with human semantic similarity judgments for 267,095 intra- and inter-modality pairs.  ...  We also evaluate a multitask dual encoder trained on both image-caption and caption-caption pairs that crucially demonstrates CxC's value for measuring the influence of intra- and inter-modality learning  ...  , Eugene Ie for their comments on the initial versions of the paper and Daphne Luong for executive support for the data collection.  ... 
arXiv:2004.15020v3 fatcat:c3k5dipdn5e6xfbl6x7haqrgkm

Semantic similarity based trust computation in websites

Hicham Ibrahim, Pradeep K. Atrey, Abdulmotaleb El Saddik
2007 Workshop on multimedia information retrieval on The many faces of multimedia semantics - MS '07  
Service • Web service which receives the texts from the Parser (i.e. through the Process Controller and Trust Computation process), and computes the current semantic similarity between two text documents  ...  The similarity measure between the two websites is computed based on a model named Latent Semantic Analysis (LSA), which will also be covered in this chapter.  ...  provided by general websites, and the breadth of the topic.  ... 
doi:10.1145/1290067.1290079 dblp:conf/mm/IbrahimAE07 fatcat:i5kpuh5wqnazxg2g2zqgmwfdz4

Novel metrics for computing semantic similarity with sense embeddings

Davide Colla, Enrico Mensa, Daniele P. Radicioni
2020 Knowledge-Based Systems  
Euclidean space, where similarity can be interpreted as a metric.  ...  However, surprisingly enough, this wealth of approaches and resources has not been supported by a parallel refinement in the metrics used to compute semantic similarity: to date, the semantic similarity  ...  Acknowledgments The second author was supported by a grant provided by Università degli Studi di Torino and Fondazione CRT, RF 2019.2263.  ... 
doi:10.1016/j.knosys.2020.106346 fatcat:4bq2ddh7nfcn5jtoc7vhzo2h3u

Assessing semantic similarity measures for the characterization of human regulatory pathways

X. Guo, R. Liu, C. D. Shriver, H. Hu, M. N. Liebman
2006 Bioinformatics  
Furthermore, we demonstrate that the functional similarity of proteins within known regulatory pathways decays rapidly as the path length between two proteins increases.  ...  In this study, we quantitatively assess the application of Gene Ontology (GO)-derived similarity measures for the characterization of direct and indirect interactions within human regulatory pathways.  ...  ACKNOWLEDGEMENTS We thank Dr Chen Yu of Monsanto Company for stimulating discussions and Nicholas Jacob, President of Windber Research Institute, for continuing support.  ... 
doi:10.1093/bioinformatics/btl042 pmid:16492685 fatcat:jcxzx2ohlzac5irvac3w6f77ay

Automatically mining software-based, semantically-similar words from comment-code mappings

Matthew J. Howard, Samir Gupta, Lori Pollock, K. Vijay-Shanker
2013 2013 10th Working Conference on Mining Software Repositories (MSR)  
In this paper, we present an automatic technique to mine semantically similar words, particularly in the software context.  ...  Many software development and maintenance tools involve matching between natural language words in different software artifacts (e.g., traceability) or between queries submitted by a user and software  ...  ACKNOWLEDGEMENTS We thank the whole Natural Language Program Analysis research group, particularly Giriprasad Sridhara, at University of Delaware.  ... 
doi:10.1109/msr.2013.6624052 dblp:conf/msr/HowardGPV13 fatcat:jrlfjahxabektctmynl42gxj2a

A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations

Camille Kurtz, Christopher F. Beaulieu, Sandy Napel, Daniel L. Rubin
2014 Journal of Biomedical Informatics  
It is based on two main steps: (1) annotation of the images with semantic terms extracted from an ontology, and (2) evaluation of the similarity of image pairs by computing the similarity between the terms  ...  However, the semantic gap between low-level image features and their high level semantics may impair the system performances.  ...  Acknowledgments The authors would like to thank Jarrett Rosenberg for his useful help on statistical evaluations.  ... 
doi:10.1016/j.jbi.2014.02.018 pmid:24632078 pmcid:PMC4058405 fatcat:movcgiinojdkpoiwemrx4oopai

Rapid Annotation of Anonymous Sequences from Genome Projects Using Semantic Similarities and a Weighting Scheme in Gene Ontology

Paolo Fontana, Alessandro Cestaro, Riccardo Velasco, Elide Formentin, Stefano Toppo, Sridhar Hannenhalli
2009 PLoS ONE  
The tool exploits for the first time an integrated approach which combines clustering of GO terms, based on their semantic similarities, with a weighting scheme which assesses retrieved hits sharing a  ...  These hits may be obtained by different methods and in this work we have based ARGOT processing on BLAST results.  ...  Acknowledgments The authors wish to thank Lorenzo Demattè for his support. Author Contributions  ... 
doi:10.1371/journal.pone.0004619 pmid:19247487 pmcid:PMC2645684 fatcat:petsul2uxvarrpr6wsoejnmn3u

Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning [article]

Junyi Bian, Baojun Lin, Ke Zhang, Zhaohui Yan, Hong Tang, Yonghe Zhang
2019 arXiv   pre-print
Here, we denote a concept of Controllable Length Control (CLC) for the trade-off between length control capacity and semantic accuracy of the language generation model.  ...  In this paper, we propose two reinforcement learning (RL) methods to adjust the trade-off between length control capacity and semantic accuracy of length control models.  ...  Therefore, it makes sense to research the control of trade-off between LC capacity and sentence quality, which we called controllable length control (CLC).  ... 
arXiv:1909.09492v1 fatcat:3qvele5o6rasxffkids6h3xxaq

Generative Adversarial Image Synthesis with Decision Tree Latent Controller [article]

Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2018 arXiv   pre-print
The DTLC has a multiple-layer tree structure in which the ON or OFF of the child node codes is controlled by the parent node codes.  ...  We evaluated the DTLC-GAN on various datasets, i.e., MNIST, CIFAR-10, Tiny ImageNet, 3D Faces, and CelebA, and confirmed that the DTLC-GAN can learn hierarchically interpretable representations with either  ...  improve the interpretability and controllability of latent codes.  ... 
arXiv:1805.10603v1 fatcat:y4sfmjwrhbdcziyoar7frm3xgy

Dual-Task Performance Reveals Increased Involvement of Executive Control in Fine Motor Sequencing in Healthy Aging

S. A. Fraser, K. Z. H. Li, V. B. Penhune
2010 The journals of gerontology. Series B, Psychological sciences and social sciences  
The purpose of the current study was to examine the role of executive control in fine motor sequencing using a motor-cognitive dual-task paradigm.  ...  Younger and older adults performed a sequential tapping task separately and concurrently with a semantic judgment task (Experiment 1) and a mental arithmetic task (Experiment 2).  ...  Acknowledgments Many thanks to Alejandro endo, Ricco Boma, Madeleine Ward, Laura Fontil, Stephanie torok, Monique Leblanc, Hilary Greenstone, Simon Desmarais-Zalob, and Vanessa Raccio who all helped with  ... 
doi:10.1093/geronb/gbq036 pmid:20478900 fatcat:7erzscqslbhvxdymxpgi2pjf2a

Executive control is shared between sentence processing and digit maintenance: Evidence from a strictly timed dual-task paradigm

Maaike Loncke, Timothy Desmet, André Vandierendonck, Robert J. Hartsuiker
2011 Journal of Cognitive Psychology  
To that end, we tested the effect of sharing executive control between sentence comprehension and the maintenance of a digit load in two dual-task experiments with strictly controlled timing (Barrouillet  ...  This finding suggests that sentence processing and the maintenance of a digit load share executive control.  ...  to capture the subtle effects of a trade-off of executive control between both tasks.  ... 
doi:10.1080/20445911.2011.586625 fatcat:tv6wxgwdf5ez7nmg74zpun3yme

Unconscious vision and executive control: How unconscious processing and conscious action control interact

Ulrich Ansorge, Wilfried Kunde, Markus Kiefer
2014 Consciousness and Cognition  
This basic distinction captures a major qualitative difference between conscious and unconscious vision.  ...  The present review focuses on one area of research, masked visual priming. This method uses visual stimuli presented in a temporal sequence to lower the visibility of one of these stimuli.  ...  The ASE model uses the flexibility of adjustments of decision thresholds to optimal speed-accuracy trade-off points as a means for exerting top-down selectivity (Norris & Kinoshita, 2008) .  ... 
doi:10.1016/j.concog.2014.05.009 pmid:24960432 fatcat:d4wkmtlukzbabptk2acp4pnkyu
« Previous Showing results 1 — 15 out of 24,986 results