Filters








175 Hits in 8.4 sec

Two birds with one stone

Lili Jiang, Jianyong Wang, Ning An, Shengyuan Wang, Jian Zhan, Lian Li
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
To address the challenge caused by name ambiguity in Web people search, this paper explores a novel graph-based framework to both disambiguate and tag people entities in Web search results.  ...  Experimental results demonstrate the effectiveness of the proposed framework in tag discovery and name disambiguation.  ...  THE FRAMEWORK FOR WEB PEOPLE NAME DISAMBIGUATION AND TAGGING 2.1 Graph Modeling Given a people name as query, let document corpus D = {d1, d2, . . . , d k } be the top k returned results from a search  ... 
doi:10.1145/1526709.1526928 dblp:conf/www/JiangWAWZL09 fatcat:s5nygwu2rzh77kqm2iyugl5js4

Categorising social tags to improve folksonomy-based recommendations

Iván Cantador, Ioannis Konstas, Joemon M. Jose
2011 Journal of Web Semantics  
Current folksonomy-based search and recommendation models exploit the social tag space as a whole to retrieve those items relevant to a tag-based query or user profile, and do not take into consideration  ...  The identification of subjective and organisational tags is based on natural language processing heuristics.  ...  In this paper, we focus on the study of the feasibility of our automatic tag categorisation proposal in a generic framework with a wide range of topics and domains.  ... 
doi:10.1016/j.websem.2010.10.001 fatcat:7femyaox3rfxzgh7xds72ibmby

Categorising Social Tags to Improve Folksonomy-Based Recommendations

Ivan Cantador, Ioannis Konstas, Joemon M. Jose
2011 Social Science Research Network  
Current folksonomy-based search and recommendation models exploit the social tag space as a whole to retrieve those items relevant to a tag-based query or user profile, and do not take into consideration  ...  The identification of subjective and organisational tags is based on natural language processing heuristics.  ...  In this paper, we focus on the study of the feasibility of our automatic tag categorisation proposal in a generic framework with a wide range of topics and domains.  ... 
doi:10.2139/ssrn.3199501 fatcat:obfkp4wqyvguvjtexnyuubo4ji

Using Word Embeddings for Ontology Enrichment

İzzet Pembeci
2016 International Journal of Intelligent Systems and Applications in Engineering  
We argue how our algorithm can be improved and augmented to make it a viable component of an ontology learning and population framework. Figure 1.  ...  In this study, we investigate if the success of word2vec, a Neural Networks based word embeddings algorithm, can be replicated in an agglutinative language like Turkish.  ...  We thank Fatma Aşık for scraping the data set we used in a clean way.  ... 
doi:10.18201/ijisae.58806 fatcat:dot2u376xbgo5jecuflgvthdiq

Publishing and Using Cultural Heritage Linked Data on the Semantic Web

Eero Hyvönen
2012 Synthesis Lectures on the Semantic Web Theory and Technology  
The methodology for representing metadata and ontological concepts 10 on the Web is based on a simple data model: a directed labeled graph, i.e., a semantic net.  ...  For example, Figure 1 .3 depicts an RDF graph telling on a metadata level that the identity p-4 is an individual of the class Person (denoted by the arc rdf:type) with name "Pablo Picasso" born in 1881  ... 
doi:10.2200/s00452ed1v01y201210wbe003 fatcat:ffncll43ubgk5bphik5wp4izxy

TiFi: Taxonomy Induction for Fictional Domains [Extended version] [article]

Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum
2019 arXiv   pre-print
A comprehensive evaluation shows that TiFi is able to construct taxonomies for a diverse range of fictional domains such as Lord of the Rings, The Simpsons or Greek Mythology with very high precision and  ...  In this paper we focus on the construction of taxonomies for fictional domains, using noisy category systems from fan wikis or text extraction as input.  ...  In this work, we utilize two distributional similarity measures, a symmetric one based on the structure of WordNet, and an asymmetric one based on word embeddings.  ... 
arXiv:1901.10263v1 fatcat:rhgd5i6qhvgonc42uaz7lsbuny

Content-based visual search learned from social media

Xirong Li
2012 ACM SIGMultimedia Records  
, Gosia and Hamdi for the ISIS dinners, Daan and Bouke for sharing conference hotels, and our secretary Virginie who helped me much in the past years.  ...  Acknowledgements Being a PhD is a non-trivial trip. I would like to use this dedicated section to thank people who practically or mentally helped me accomplish the trip.  ...  In [100] , for instance, the authors train a visual classifier on web image search results of a given category, and re-rank the search results by the classifier.  ... 
doi:10.1145/2206765.2206774 fatcat:kxk6kciwhfe2hcqw546ez2coku

A Review Of Natural Language Processing Research

Erik Cambria
2017 Zenodo  
This review paper draws on recent developments in NLP research to look at the past, present, and future of NLP technology in a new light.  ...  Natural language processing (NLP) is a theory-motivated range of computational techniques for the automatic analysis and representation of human language.  ...  for text processing, based on two unsupervised methods for keyword and sentence extraction.  ... 
doi:10.5281/zenodo.1000804 fatcat:6extpvzeibbwfenkwwehz5dcdq

SentiHealth: creating health-related sentiment lexicon using hybrid approach

Muhammad Zubair Asghar, Shakeel Ahmad, Maria Qasim, Syeda Rabail Zahra, Fazal Masud Kundi
2016 SpringerPlus  
The Web is a huge repository of facts and opinions available for people around the world about a particular product, service, issue, policy and health-care (Liu 2011).  ...  The proposed approach is based on the bootstrapping modal, a dataset of health reviews, and corpus-based sentiment detection and scoring.  ...  It tags meanings of emotions with concepts taken from WordNet and assist in resolving the issue of word sense disambiguation.  ... 
doi:10.1186/s40064-016-2809-x pmid:27504237 pmcid:PMC4954801 fatcat:hta5bb2f45eobmqr355drrqu4a

Recent advances in methods of lexical semantic relatedness – a survey

ZIQI ZHANG, ANNA LISA GENTILE, FABIO CIRAVEGNA
2012 Natural Language Engineering  
It is recognised that a fundamental task in Information Extraction is Named Entity Recognition, the goals of which are identifying references of named entities in unstructured documents, and classifying  ...  Resolving ambiguity concerns recognising the true referent entity of a name reference, essentially a further named entity 'recognition' step and often a compulsory pro-VI  ...  When a graph is built based on connections defined in a knowledge base, it can be considered as a branch of knowledge based methods; on the other hand, in many cases, graph based algorithms are applied  ... 
doi:10.1017/s1351324912000125 fatcat:b62qbqwrqfaf3gytw22yktc5ae

Learning Probabilistic Models of Word Sense Disambiguation [article]

Ted Pedersen
2007 arXiv   pre-print
The supervised methods focus on performing model searches through a space of probabilistic models, and the unsupervised methods rely on the use of Gibbs Sampling and the Expectation Maximization (EM) algorithm  ...  An explanation for this success is presented in terms of learning rates and bias-variance decompositions.  ...  For example, if an instance of bill is being disambiguated and it is known that two sentences earlier bill refers to a bird jaw then it seems unlikely that the current occurrence is being used in the sense  ... 
arXiv:0707.3972v1 fatcat:c452544gqrgxvk7sb7toetv3si

Human Computation

Edith Law, Luis von Ahn
2011 Synthesis Lectures on Artificial Intelligence and Machine Learning  
With the growth of the Web, human computation systems can now leverage the abilities of an unprecedented number of people via the Web to perform complex computation.  ...  , including AI, Machine Learning, HCI, Mechanism/Market Design and Psychology, and capturing their unique perspectives on the core research questions in human computation; and (4) suggesting promising  ...  Acknowledgments As a relatively young field, the idea of human computation is not yet well defined.This book is in part an accumulation of ideas from people in the field with whom we had discussions and  ... 
doi:10.2200/s00371ed1v01y201107aim013 fatcat:fxuui3q2yrgddf5ewih562zgza

D6.1 – Specification of the data interchange format, initial version

Karel Braeckman, Simon Debacq, Harri Kiiskinen, Lauri Saarikoski, Wim Van Lancker, Dieter Van Rijsselbergen, Maarten Verwaest, Kim Viljanen
2019 Zenodo  
This deliverable defines the functional and non-functional requirements of the MeMAD prototype system, based on input concerning the tools developed in WP2, WP3, WP4 and WP5 and based on the project's  ...  We then identify relevant stakeholders and processes for the project's prototypes from the media production and consumption chain.  ...  One way is that, for content that has been tagged manually by archivists, the manual tagging metadata has been augmented by named entity recognition and disambiguation.  ... 
doi:10.5281/zenodo.4818025 fatcat:y5egnqb63fgd3hi6dape4nqxwe

From Frequency to Meaning: Vector Space Models of Semantics

P. D. Turney, P. Pantel
2010 The Journal of Artificial Intelligence Research  
Our goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs for those who are already familiar with the area, and to provide pointers into  ...  This paper surveys the use of VSMs for semantic processing of text. We organize the literature on VSMs according to the structure of the matrix in a VSM.  ...  Thanks to Arkady Borkovsky and Eric Crestan for developing the distributed sparse-matrix multiplication algorithm, and to Marco Pennacchiotti for his invaluable comments.  ... 
doi:10.1613/jair.2934 fatcat:vmbzpass3vezjmmtknzi4zcrre

User-Generated Content in Social Media (Dagstuhl Seminar 17301)

Tat-Seng Chua, Norbert Fuhr, Gregory Grefenstette, Kalervo Järvelin, Jaakko Paltonen, Marc Herbstritt
2018 Dagstuhl Reports  
WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.  ...  This report documents the program and the outcomes of Dagstuhl Seminar 17301 "User-Generated Content in Social Media". Social media have a profound impact on individuals, businesses, and society.  ...  two independent factor graphs.  ... 
doi:10.4230/dagrep.7.7.110 dblp:journals/dagstuhl-reports/ChuaFGJP17 fatcat:bman5u6q5zdg7a6csnzwpba7sm
« Previous Showing results 1 — 15 out of 175 results