Filters








2,575 Hits in 4.7 sec

LODDO: Using Linked Open Data Description Overlap to Measure Semantic Relatedness between Named Entities [chapter]

Wenlei Zhou, Haofen Wang, Jiansong Chao, Weinan Zhang, Yong Yu
2012 Lecture Notes in Computer Science  
LOD consists of lots of data sources from different domains and provides rich a priori knowledge about the entities in the world.  ...  the existing knowledge based approaches have the entity coverage issue and the statistical based approaches have unreliable result to low frequent entities, we propose a more comprehensive approach by leveraging  ...  As DBpedia is extracted from Wikipedia, and Wikipedia has a larger coverage than WordNet, we can conclude that LOD does enlarge entity coverage tremendously than Wikipedia and WordNet.  ... 
doi:10.1007/978-3-642-29923-0_18 fatcat:hnvur6r22rgknl6o4ocbkbhbo4

N-ary relation extraction for simultaneous T-Box and A-Box knowledge base augmentation

Marco Fossati, Emilio Dorigatti, Claudio Giuliano, Philipp Cimiano
2018 Semantic Web Journal  
The system implements four research contributions: it (1) executes n-ary relation extraction by applying the frame semantics linguistic theory, as opposed to binary techniques; it (2) simultaneously populates  ...  We assess our approach by setting the target KB to DBpedia and by considering a use case of 52, 000 Italian Wikipedia soccer player articles.  ...  Frames intrinsically bear n-ary relations through FEs, while RDF naturally represents binary relations. Hence, we need a method to express FEs relations in RDF, namely reification.  ... 
doi:10.3233/sw-170269 fatcat:57vi4zpyivgsjmqdxna5zegmya

Towards Temporal Scoping of Relational Facts based on Wikipedia Data

Avirup Sil, Silviu-Petru Cucerzan
2014 Proceedings of the Eighteenth Conference on Computational Natural Language Learning  
Most previous work in information extraction from text has focused on named-entity recognition, entity linking, and relation extraction.  ...  Less attention has been paid given to extracting the temporal scope for relations between named entities; for example, the relation president-Of(  ...  Extracting Relevant Sentences For every relation, we extract slot-filler names from infoboxes of each Wikipedia article.  ... 
doi:10.3115/v1/w14-1612 dblp:conf/conll/SilC14 fatcat:qntbyhqkdff5jip5dopcizmfnq

Relation Extraction with Relation Topics

Chang Wang, James Fan, Aditya Kalyanpur, David Gondek
2011 Conference on Empirical Methods in Natural Language Processing  
First, we construct a large relation repository of more than 7,000 relations from Wikipedia.  ...  Instead of relying only on the training instances for a new relation, we leverage the knowledge learned from previously trained relation detectors.  ...  Extracting Relations from Wikipedia Our training data is from two parts: relation instances from DBpedia (extracted from Wikipedia infoboxes), and sentences describing the relations from the corresponding  ... 
dblp:conf/emnlp/WangFKG11 fatcat:7bepc2yiwvattdpyzshzwoh6nm

An Intrinsic and Extrinsic Evaluation of Learned COVID-19 Concepts using Open-Source Word Embedding Sources (Preprint)

Soham Parikh, Anahita Davoudi, Shun Yu, Carolina Giraldo, Emily Schriver, Danielle Mowery
2020 JMIR Medical Informatics  
These efforts could be improved by leveraging documented, COVID-19-related symptoms, findings, and disorders from clinical text sources in the electronic health record.  ...  Given an initial lexicon of COVID-19-related terms, characterize the returned terms by similarity across various, open-source word embeddings and determine common semantic and syntactic patterns between  ...  To accurately characterize each patient's COVID-19 profile for study, we must develop natural language processing systems to reliably extract COVID-19-related information.  ... 
doi:10.2196/21679 pmid:33544689 fatcat:mrlumhpfyze33ibujujulth3aa

Information Extraction from Scientific Literature for Method Recommendation [article]

Yi Luan
2018 arXiv   pre-print
Latent relations between scientific terms can be learned from the graph. Recommendations will be made through graph inference for both observed and unobserved relational pairs.  ...  external resources such as Wikipedia.  ...  Figure 10 : 10 Graph with auxiliary relations from different resources: Yellow arches are relations from Wikipedia sections; Grey arches are dependency relations extracted from text where the two terms  ... 
arXiv:1901.00401v1 fatcat:owygelspnjblloa2eecf5etihe

An Intrinsic and Extrinsic Evaluation of Learned COVID-19 Concepts using Open-Source Word Embedding Sources [article]

Soham Parikh, Anahita Davoudi, Shun Yu, Carolina Giraldo, Emily Schriver, Danielle Mowery
2021 medRxiv   pre-print
These efforts could be improved by leveraging documented, COVID-19-related symptoms, findings, and disorders from clinical text sources in the electronic health record.  ...  Word embeddings can identify terms related to these clinical concepts from both the biomedical and non-biomedical domains and are being shared with the open-source community at large.  ...  To accurately characterize each patient's COVID-19 profile for study, we must develop natural language processing (NLP) systems to reliably extract COVID-19-related information.  ... 
doi:10.1101/2020.12.29.20249005 fatcat:hlm72q7vgfcrzgy7jre4gpmbea

Relational Inference for Wikification

Xiao Cheng, Dan Roth
2013 Conference on Empirical Methods in Natural Language Processing  
relations in text helps both candidate generation and ranking Wikipedia titles considerably.  ...  Wikification, commonly referred to as Disambiguation to Wikipedia (D2W), is the task of identifying concepts and entities in text and disambiguating them into the most specific corresponding Wikipedia  ...  We determine the weights by combining type and confidence of the relation extracted from text with the confidence in relations retrieved from an external Knowledge Base (KB) by using the mention pairs  ... 
dblp:conf/emnlp/ChengR13 fatcat:bcdkudbhezfefms5rji43cbcey

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

Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum
2019 arXiv   pre-print
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.  ...  Taxonomies are important building blocks of structured knowledge bases, and their construction from text sources and Wikipedia has received much attention.  ...  Relying largely on pattern-based extraction, the data from WebisALOD is very noisy, especially beyond the top-confidence ranks.  ... 
arXiv:1901.10263v1 fatcat:rhgd5i6qhvgonc42uaz7lsbuny

Open-Domain Question Answering Framework Using Wikipedia [chapter]

Saleem Ameen, Hyunsuk Chung, Soyeon Caren Han, Byeong Ho Kang
2016 Lecture Notes in Computer Science  
To investigate this, we implemented an algorithmic process that extracted the target entity from the question using CRF based named entity recognition (NER) and utilised all remaining words as potential  ...  This paper explores the feasibility of implementing a model for an open domain, automated question and answering framework that leverages Wikipedia's knowledgebase.  ...  These qualities are a subset of intrinsic characteristics related to the labelled entity's type as opposed to the explicit characteristics or experiences of the extracted entity.  ... 
doi:10.1007/978-3-319-50127-7_55 fatcat:hcnklhkow5gfdf4ts5ldvcylwq

A Large-Scale Characterization of How Readers Browse Wikipedia [article]

Tiziano Piccardi, Martin Gerlach, Akhil Arora, Robert West
2022 arXiv   pre-print
Using billions of page requests from Wikipedia's server logs, we measure how readers reach articles, how they transition between articles, and how these patterns combine into more complex navigation paths  ...  We show that Wikipedia navigation paths commonly mesh with external pages as part of a larger online ecosystem, and we describe how naturally occurring navigation paths are distinct from targeted navigation  ...  By analyzing billions of navigation traces extracted from the logs (Sec. 3), we span three levels of aggregation in our research questions: (1) Unigram level: How do readers reach Wikipedia articles?  ... 
arXiv:2112.11848v2 fatcat:rcqxbkux5jdhzlibjxlo56xnsq

Similarities, challenges and opportunities of Wikipedia content and open source projects

Andrea Capiluppi
2012 Journal of Software: Evolution and Process  
" we isolate valuable content in both Wikipedia pages and OSS projects.  ...  Similarly, other online content portals (like Wikipedia) could be harvested for valuable content.  ...  Other relations are weaker, and show for example that there's little relation between the amount of links to external websites in a Wikipedia page, and the amount of other Wikipedia pages linked by the  ... 
doi:10.1002/smr.1570 fatcat:2rfv77bshrg3rj2acjen3limna

Mining meaning from Wikipedia

Olena Medelyan, David Milne, Catherine Legg, Ian H. Witten
2009 International Journal of Human-Computer Studies  
It focuses on research that extracts and makes use of the concepts, relations, facts and descriptions found in Wikipedia, and organizes the work into four broad categories: applying Wikipedia to natural  ...  language processing; using it to facilitate information retrieval and information extraction; and as a resource for ontology building.  ...  Medelyan is supported by a scholarship from Google, Milne by the New Zealand Tertiary Education Commission.  ... 
doi:10.1016/j.ijhcs.2009.05.004 fatcat:mzxszf4jlfcizbgxuemgdwzdiy

From information to knowledge

Gerhard Weikum, Martin Theobald
2010 Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems of data - PODS '10  
This is enabled by the advent of knowledge-sharing communities such as Wikipedia and the progress in automatically extracting entities and relationships from semistructured as well as natural-language  ...  The goal is to automatically construct and maintain a comprehensive knowledge base of facts about named entities, their semantic classes, and their mutual relations as well as temporal contexts, with high  ...  Leveraging existing knowledge.  ... 
doi:10.1145/1807085.1807097 dblp:conf/pods/WeikumT10 fatcat:vtgbi6sjafgsrhmnlztf6q5mxu

Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces

Lluis Gomez, Yash Patel, Marcal Rusinol, Dimosthenis Karatzas, C. V. Jawahar
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique.  ...  End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible.  ...  A semantic analysis of the data, extracted from the ground-truth of relevance assessments for the ImageCLEF retrieval queries, is shown in Figure 3 .  ... 
doi:10.1109/cvpr.2017.218 dblp:conf/cvpr/Gomez-BigordaPR17 fatcat:paymsbngcbfblfp5ehxgnk3gpm
« Previous Showing results 1 — 15 out of 2,575 results