Filters








4,087 Hits in 6.5 sec

TermPedia for interactive document enrichment using technical terms to provide relevant contextual information

Proscovia Olango, Gerwin Kramer, Gosse Bouma
2009 2009 International Multiconference on Computer Science and Information Technology  
TableII shows that the page with id 2142761 on "Leukapheresis" has a link to the Wikipedia page "Blood plasma" with anchor text "Plasma". B.  ...  This experiment was inspired by the work done by [11] , who link documents to Wikipedia with the help of anchor text. For more information about anchor text, please see section III-A4 of this paper.  ... 
doi:10.1109/imcsit.2009.5352716 dblp:conf/imcsit/OlangoKB09 fatcat:xd7b6xhhk5g7bpt3dl4a3ixyu4

Linking wikipedia to the web

Rianne Kaptein, Pavel Serdyukov, Jaap Kamps
2010 Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '10  
Such external links significantly extend the information in Wikipedia with information from the Web at large, while retaining the encyclopedic organization of Wikipedia.  ...  We use a language modeling approach to create a full-text and anchor text runs, and experiment with different document priors.  ...  Acknowledgments The test collection for Wikipedia external link detection is available at http://staff.science.uva.nl/~kamps/effort/data.  ... 
doi:10.1145/1835449.1835642 dblp:conf/sigir/KapteinSK10 fatcat:bu5u7ukmarefvj7iwujej7uxcq

OTNEL: A Distributed Online Deep Learning Semantic Annotation Methodology

Christos Makris, Michael Angelos Simos
2020 Big Data and Cognitive Computing  
Our novel methodology evaluates polysemous anchor mentions with sense compatibility based on thematic segmentation of the Wikipedia knowledge graph representation.  ...  In this work, we introduce a distributed, supervised deep learning methodology employing a long short-term memory-based deep learning architecture model for entity linking with Wikipedia.  ...  The current work relies on semantic information from hyperlink anchors to Wikipedia entities.  ... 
doi:10.3390/bdcc4040031 fatcat:vftpewqo7vfzfai4x37bm2xyym

Generating links to background knowledge

Jiyin He, Maarten de Rijke, Merlijn Sevenster, Rob van Ommering, Yuechen Qian
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
Automatically annotating texts with background information has recently received much attention.  ...  Direct applications of existing automatic link generation systems trained on Wikipedia to our radiology data do not yield satisfactory results.  ...  For anchor texts that have multiple candidate target pages labeled "link," we choose the one with the highest prediction confidence.  ... 
doi:10.1145/2063576.2063845 dblp:conf/cikm/HeRSOQ11 fatcat:qsfavrxafvgsngnzrresbqa2le

Aligning Knowledge and Text Embeddings by Entity Descriptions

Huaping Zhong, Jianwen Zhang, Zhen Wang, Hai Wan, Zheng Chen
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
Wang et al. (2014a) rely on Wikipedia anchors, making the applicable scope quite limited.  ...  In this paper we propose a new alignment model based on text descriptions of entities, without dependency on anchors.  ...  Compared to the method of alignment using Wikipedia anchors Wang et al. (2014a) , our method has no dependency on special data sources of anchors and hence can be applied to any knowledge bases with text  ... 
doi:10.18653/v1/d15-1031 dblp:conf/emnlp/ZhongZWWC15 fatcat:6te5aslqpfdw7fyppamc24tndq

Temporal Anchor Text as Proxy for Real User Queries

Thaer Samar, Arjen P. de Vries
2015 International Conference on Theory and Practice of Digital Libraries  
Our approach is to rank anchor text based on their popularity in the archive at specific time. Then, we check the importance of the top ranked anchor text in the public Web at the same time.  ...  First, we study the link graph of four years of Web archive in order to show how the target hosts and anchor text evolve over time. Second, we investigate the importance of anchor text over time.  ...  Based on the one-month granularity, on average 26% of all anchor text over all months has an exact match with a Wikipedia title (using all domains).  ... 
dblp:conf/ercimdl/SamarV15 fatcat:obejw4w7q5a3xcapvnok7liyoq

Text Semantic Annotation: A Distributed Methodology Based on Community Coherence

Christos Makris, Georgios Pispirigos, Michael Angelos Simos
2020 Algorithms  
In this paper we introduce a novel distributed supervised knowledge-based methodology employing community detection algorithms for text annotation with Wikipedia Entities, establishing the unprecedented  ...  Text annotation is the process of identifying the sense of a textual segment within a given context to a corresponding entity on a concept ontology.  ...  European Union and the Greek national funds through the Regional Operational Program "Western Greece 2014-2020", under the Call "Regional Research and Innovation Strategies for Smart Specialization-RIS3 in Information  ... 
doi:10.3390/a13070160 fatcat:znccdtd5wreprdhjlus7tyso3m

Link Discovery: A Comprehensive Analysis

Nicolai Erbs, Torsten Zesch, Iryna Gurevych
2011 2011 IEEE Fifth International Conference on Semantic Computing  
Simulating other document collections with fewer links, we show that text-based approaches yield better results.  ...  We classify link discovery approaches with respect to the type of knowledge being used: the text of a document, its title, and already existing links.  ...  Another problem with link-based approaches trained on Wikipedia is that they cannot be easily transferred to other document collections.  ... 
doi:10.1109/icsc.2011.63 dblp:conf/semco/ErbsZG11 fatcat:4wl4om6cyvbj5i4gq5t6oldvke

Linking Entities in Tweets to Wikipedia Knowledge Base [chapter]

Xianqi Zou, Chengjie Sun, Yaming Sun, Bingquan Liu, Lei Lin
2014 Communications in Computer and Information Science  
We use Wikipedia articles information to generate enough entity candidates, and as far as possible eliminate ambiguity candidates to get higher coverage and less quantity.  ...  Entity linking has received much more attention. The purpose of entity linking is to link the mentions in the text to the corresponding entities in the knowledge base.  ...  For the text information and non-text information related with entities, we make use of the Wikipedia API to get them.  ... 
doi:10.1007/978-3-662-45924-9_33 fatcat:piinztr3mrdgvopbktfdclen44

Completing wikipedia's hyperlink structure through dimensionality reduction

Robert West, Doina Precup, Joelle Pineau
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
' link already present in Wikipedia.  ...  Instead, it is based on principal component analysis, a well-founded mathematical generalization technique, and predicts new links purely based on the statistical structure of the graph formed by the existing  ...  Links marked with a star could actually be added because the appropriate anchor text occurred in the source article.  ... 
doi:10.1145/1645953.1646093 dblp:conf/cikm/WestPP09 fatcat:6ggfym4bhzfpphh36emxktmfim

Building a Corpus for Japanese Wikification with Fine-Grained Entity Classes

Davaajav Jargalsaikhan, Naoaki Okazaki, Koji Matsuda, Kentaro Inui
2016 Proceedings of the ACL 2016 Student Research Workshop  
All entity mentions are labeled by a fine-grained semantic classes (200 classes), and 19,121 mentions were successfully linked to Japanese Wikipedia articles.  ...  Even with the fine-grained semantic classes, we found it hard to define the target of entity linking annotations and to utilize the fine-grained semantic classes to improve the accuracy of entity linking  ...  Acknowledgments This work was partially supported by Research and Development on Real World Big Data Integration and Analysis, MEXT and JSPS KAKENHI Grant number 15H05318.  ... 
doi:10.18653/v1/p16-3021 dblp:conf/acl/JargalsaikhanOM16 fatcat:7uiylip3efc47edlopwap7euha

A Pipeline Japanese Entity Linking System with Embedding Features

Shuangshuang Zhou
2016 Pacific Asia Conference on Language, Information and Computation  
For candidate generation, we find that a concept dictionary using anchor texts of Wikipedia is more effective than methods based on surface similarity.  ...  Entity linking (EL) is the task of connecting mentions in texts to entities in a large-scale knowledge base such as Wikipedia.  ...  We call the surface texts of hyper-links anchor texts.  ... 
dblp:conf/paclic/Zhou16 fatcat:oe53hhg2svcllotp4y2rdbxdba

Local and Global Algorithms for Disambiguation to Wikipedia

Lev-Arie Ratinov, Dan Roth, Doug Downey, Mike Anderson
2011 Annual Meeting of the Association for Computational Linguistics  
Disambiguation to Wikipedia is similar to a traditional Word Sense Disambiguation task, but distinct in that the Wikipedia link structure provides additional information about which disambiguations are  ...  The comprehensiveness of Wikipedia has made the online encyclopedia an increasingly popular target for disambiguation.  ...  T i is taken to be the set of titles most frequently linked to with anchor text m i in Wikipedia.  ... 
dblp:conf/acl/RatinovRDA11 fatcat:oxzpza3vjraffiryqoqkjpxqpi

DAMSEL: The DSTO/Macquarie System for Entity-Linking

Matthew Honnibal, Robert Dale
2009 Text Analysis Conference  
This paper describes the DSTO/Macquarie University System for Entity Linking (DAMSEL), which competed in the 2009 Text Acquisition Conference Knowledge Base Population task.  ...  Wikipedia authors can anchor these links with arbitrary text, allowing them to realise the entity mention however they like.  ...  Finally, we can find a similar source of information in the text used to anchor links between pages.  ... 
dblp:conf/tac/HonnibalD09 fatcat:hlecg32n2vdl5o76jt7liwrv7a

Combining Multiple Signals for Semanticizing Tweets: University of Amsterdam at #Microposts2015

Cristina Gârbacea, Daan Odijk, David Graus, Isaac Sijaranamual, Maarten de Rijke
2015 Workshop on Making Sense of Microposts  
We consider alternatives for dealing with ambiguity that can help in the named entity extraction and linking processes.  ...  We describe a diverse set of approaches based on the Semanticizer, an open-source entity linking framework developed at the University of Amsterdam, adapted to the task of the #Microposts2015 challenge  ...  Description linkOccCount no. of times mention appears as anchor text on Wikipedia linkDocCount no. of docs in which mention appears as anchor text occCount no. of times the mention appears on Wikipedia  ... 
dblp:conf/msm/GarbaceaOGSR15 fatcat:ubmeqrgnqzcjlhpjwf6v6bkhte
« Previous Showing results 1 — 15 out of 4,087 results