Filters








82,718 Hits in 3.4 sec

Preliminary Results for Biomedical Word Sense Disambiguation Based on Semantic Clustering

Tamara Martin-Wanton, Rafael Berlanga-Llavori, Antonio Jimeno-Yepes
2011 2011 22nd International Workshop on Database and Expert Systems Applications  
Knowledge-based methods compare the context of the ambiguous word to the information available in the terminological resource, but their main purpose is not only word sense disambiguation.  ...  In this work, we rely on a Knowledge Resource (KR) which provides both an inventory of concepts and their lexical information.  ...  But identified candidate senses might not correlate with all the senses in reference terminological resources.  ... 
doi:10.1109/dexa.2011.66 dblp:conf/dexaw/Martin-WantonLJ11 fatcat:hsqeyuvzo5h5behjkzkpp2zof4

Building a consistent Information System in the different nodes and defining standardisation strategies

David, Hollebecq, Neveu
2019 Zenodo  
persistent, unambiguous, resolvable Variable naming and formalization Give (local or global) name to variables What (concept), How, Associated controlled contexts Data interoperability Formats, schemas, semantic  ...  In an ideal world identifier should be unique for each object (bijection), In practice this is rarely the case. Object Identification Non ambiguous An identifier only stands for one resource.  ...  How do we want to identify? good identifier. ID36B2 ID36B2 Object Identification Non ambiguous An identifier only stands for one resource.  ... 
doi:10.5281/zenodo.3358832 fatcat:7x7jvp2o3zdptgpgv775bqzf3e

Identification of objects with Uniform Resource Identifier (URI): recommendations for application in plant phenotyping

Jean-Eudes Hollebecq, Llorenç Cabrera-Bosquet, Romain David, Quidoz Marie-Claude, Tardieu François, Tireau Anne, Pascal Neveu
2019 Zenodo  
In order to fill their purpose, identifiers must have some properties, namely non-ambiguousness, unicity, persistence, resolvability, stability.  ...  However, it is also a big issue when designing a persistent identifier (e.g. usable in more than twenty years) and an important drawback if people put too much semantics in it.  ...  Ideally we want to identify everything, but we have very different resources, do we identify them in the same way? Are URIs the best option to identify these resources?  ... 
doi:10.5281/zenodo.3560629 fatcat:fl3tlys5prcr5gohevehucrimq

Semantic Heterogeneity Issues on the Web

Jorge Gracia, Eduardo Mena
2012 IEEE Internet Computing  
The Web's natural semantic heterogeneity presents problems, however -namely, redundancy and ambiguity.  ...  To operate effectively, the Semantic Web must be able to make explicit the semantics of Web resources via ontologies, which software agents use to automatically process these resources.  ...  Furthermore, our approach deals with ontology terms, whereas CRS deals with resource identifiers, whether or not they constitute semantic descriptions.  ... 
doi:10.1109/mic.2012.116 fatcat:jcgs5qatcjgg3eatv6nhqlw65a

SDF: A Sign Description Framework for Cross-Context Information Resource Representation and Interchange

Jingzhi Guo
2014 2014 Enterprise Systems Conference  
To semantically represent information resources, this paper proposes a novel Sign Description Framework, which is an abstract specification that represents any object in reality as signs.  ...  Based on a quaternary model of sign in semiotics, the proposed framework has several advantages such as nonambiguity of resource representation in meaning, easy resource modeling, and easy cross-context  ...  In Table III , we compare SDF with RDF in the aspects of resource ambiguity, resource description (or resource modeling), resource cross-context ability, and reification ambiguity. Easy.  ... 
doi:10.1109/es.2014.32 dblp:conf/es/Guo14 fatcat:z5mtbr25grhnlbayubtuybnyry

Query Expansion for UMLS Metathesaurus Disambiguation Based on Automatic Corpus Extraction

Antonio Jimeno Yepes, Alan R. Aronson
2010 2010 Ninth International Conference on Machine Learning and Applications  
On the other hand, manually annotated data is limited, and covering all the ambiguous cases of a large resource like the UMLS is infeasible.  ...  We have focused on the extraction of collocations which might be used in combination with one of the senses of the ambiguous terms.  ...  This set contains 50 ambiguous terms and annotations of UMLS semantic types. In addition, there is a mapping to the UMLS concept unique identifiers (CUI) for the 1999 version.  ... 
doi:10.1109/icmla.2010.154 dblp:conf/icmla/YepesA10 fatcat:nsv2citchncchj6rmii4una3ju

UIMA2LOD: Integrating UIMA Text Annotations into the Linked Open Data Cloud [chapter]

Claudia Bretschneider, Heiner Oberkampf, Sonja Zillner
2015 Communications in Computer and Information Science  
: Hash code representing all features (names and values) • Combined into URL as unique identifier for resource "cm"^^ xsd:Incorrect calculation of identifiers for resources leads to ambiguities in assignment  ...  measuresTriplification -(3) Resolution of Ambiguities with Unique IDs• Incorrect calculation of identifiers for resources leads to ambiguities in assignment of featureName and featureValue • Our approach  ...  Semantic Annotations Axillary lymph node with diameter 1.5 cm. Structural Annotations Case Study on Integrating RDF Annotations into the Model for Clinical Information (MCI)  ... 
doi:10.1007/978-3-319-24543-0_2 fatcat:okwizaigwrfatksxq245rbcijq

Enhancing semantic relation quality of UMLS knowledge sources

Demeke Ayele, Jean-Pierre Chevallet, Getnet Kassie, Million Meshesha
2012 Proceedings of the International Conference on Management of Emergent Digital EcoSystems - MEDES '12  
In this article, we presented an integrated approach for enhancing the quality of semantic tuples in the UMLS knowledge sources.  ...  Most biomedical semantic resources have been developed for different contexts focusing on the structural representation but with less attention on the acceptability and naturalness of the individual semantic  ...  in identifying and circumvent multiple types of inconsistencies and ambiguities in the UMLS resources.  ... 
doi:10.1145/2457276.2457289 dblp:conf/medes/AyeleCKM12 fatcat:j77kvewzlnfjphdigrw7ywuzw4

Preserving Meaning, Not Just Objects: Semantics and Digital Preservation

David Dubin, Joe Futrelle, Joel Plutchak, Janet Eke
2009 Library Trends  
This article describes project efforts to identify the core underlying semantic issues affecting long-term digital preservation, and to model how semantic inference may help next-generation archives head  ...  To support on-the-ground preservation efforts in existing technical and organizational environments, we have developed tools to help curators collect and manage Web-based digital resources, such as the  ...  project to identify semantic ambiguity in real-world metadata descriptions and highlight potential preservation risks.  ... 
doi:10.1353/lib.0.0054 fatcat:en2mf4tasvajxb4cx3kiy5pkm4

Enabling Folksonomies for Knowledge Extraction

Andrés García-Silva, Iván Cantador, Oscar Corcho
2012 International Journal on Semantic Web and Information Systems (IJSWIS)  
However, when it comes to understanding the meaning of tags in folksonomies, several problems mainly related to the appearance of synonymous and ambiguous tags arise, specifically in the context ofmultilinguality  ...  Folksonomies emerge as the result of the free tagging activity of a large number of users over a variety of resources.  ...  If there is only one resource (i.e., the tag is not ambiguous) we select it as To deal with ambiguous tags we first process the tag context in an Active Context Selection process, so that we identify  ... 
doi:10.4018/jswis.2012070102 fatcat:2bds2l3fvna25njsh3ws3ple4y

Word Sense Disambiguation [chapter]

2013 Natural Language Processing  
The effectiveness of knowledge-based word sense disambiguation (WSD) approaches depends in part on the information available in the reference knowledge resource.  ...  Assignment of collocations to a candidate sense based on UMLS semantic group profiles is more effective in the AEC method.  ...  We are interested in identifying this missing content automatically and transferring contextual information of ambiguous words to existing resources.  ... 
doi:10.1201/b15472-14 fatcat:7c3vrxnc75ec3boxhqmcqhtieq

Collocation analysis for UMLS knowledge-based word sense disambiguation

Antonio Jimeno-Yepes, Bridget T Mclnnes, Alan R Aronson
2011 BMC Bioinformatics  
The effectiveness of knowledge-based word sense disambiguation (WSD) approaches depends in part on the information available in the reference knowledge resource.  ...  Assignment of collocations to a candidate sense based on UMLS semantic group profiles is more effective in the AEC method.  ...  We are interested in identifying this missing content automatically and transferring contextual information of ambiguous words to existing resources.  ... 
doi:10.1186/1471-2105-12-s3-s4 pmid:21658291 pmcid:PMC3111590 fatcat:wr7ncewhjbgtzlim2cpvavl4b4

Review of the state of the art: discovering and associating semantics to tags in folksonomies

Andrés García-Silva, Oscar Corcho, Harith Alani, Asunción Gómez-Pérez
2012 Knowledge engineering review (Print)  
This paper describes and compares the most relevant approaches for associating tags with semantics in order to make explicit the meaning of those tags.  ...  problems that appear during the semantic association process.  ...  In general, this type of analysis is more focused on identifying the existence of ambiguity, rather than on identifying the true meaning of a tag.  ... 
doi:10.1017/s026988891100018x fatcat:rb2adgubx5dc5lzhrzldqwjrbq

Knowledge-based and knowledge-lean methods combined in unsupervised word sense disambiguation

Antonio Jimeno Yepes, Alan R. Aronson
2012 Proceedings of the 2nd ACM SIGHIT symposium on International health informatics - IHI '12  
Knowledge-based methods compare the context of the ambiguous word to the information available in a terminological resource, but their main purpose is not word sense disambiguation.  ...  resource as a catalog for candidate senses.  ...  Acknowledgment This work was supported in part by the Intramural Research Program of the NIH, National Library of Medicine and by an appointment of A.  ... 
doi:10.1145/2110363.2110449 dblp:conf/ihi/Jimeno-YepesA12 fatcat:khklixsv3bfvrofhilcopig2fq

Associating Semantics to Multilingual Tags in Folksonomies

Andrés García-Silva, Óscar Corcho, Jorge Gracia
2010 International Conference Knowledge Engineering and Knowledge Management  
We use DBpedia [2] as semantic resource to define the tag meanings.  ...  However, the lack of semantics and multilinguality hamper information retrieval process based on folksonomies. In this paper we propose an approach to bring semantics to multilingual folksonomies.  ...  RELATED WORK The problem of identifying tag semantics in Folksonomies has been addressed by researchers in two complementary ways: 1) by identifying groups of related tags using clustering techniques in  ... 
dblp:conf/ekaw/Garcia-SilvaCG10 fatcat:vicc24m2jrcblgpjbyxo53d3wi
« Previous Showing results 1 — 15 out of 82,718 results