Automatic Semantic Web Annotation of Named Entities

Charton, Éric; Gagnon, Michel; Ozell, Benoı̂t

doi:10.1007/978-3-642-21043-3_10

Cited by 15 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It tries to link each detected named entity with an entity in DBpedia based on a disambiguation process that is described in Charton et al. 57 Wikimeta API is compliant with REST and the responses are formatted in XML and JSON. The datasets used to train the NLP tools of Wikimeta are derived from Wikipedia.…”

Section: Lod-based Nee Tools Of General Purposementioning

confidence: 99%

Exploiting Linked Data for Open and Configurable Named Entity Extraction

Fafalios

Baritakis

Tzitzikas

2015

Int. J. Artif. Intell. Tools

View full text Add to dashboard Cite

Named Entity Extraction (NEE) is the process of identifying entities in texts and, very commonly, linking them to related (Web) resources. This task is useful in several applications, e.g. for question answering, annotating documents, post-processing of search results, etc. However, existing NEE tools lack an open or easy configuration although this is very important for building domain-specific applications. For example, supporting a new category of entities, or specifying how to link the detected entities with online resources, is either impossible or very laborious. In this paper, we show how we can exploit semantic information (Linked Data) at real-time for configuring (handily) a NEE system and we propose a generic model for configuring such services. To explicitly define the semantics of the proposed model, we introduce an RDF/S vocabulary, called "Open NEE Configuration Model", which allows a NEE service to describe (and publish as Linked Data) its entity mining capabilities, but also to be dynamically configured. To allow relating the output of a NEE process with an applied configuration, we propose an extension of the Open Annotation Data Model which also enables an application to run advanced queries over the annotated data. As a proof of concept, we present X-Link, a fully-configurable NEE framework that realizes this approach. Contrary to the existing tools, X-Link allows the user to easily define the categories of entities that are interesting for the application at hand by exploiting one or more semantic Knowledge Bases. The user is also able to update a category and specify how to semantically link and enrich the identified entities. This enhanced configurability allows X-Link to be easily configured for different contexts for building domain-specific applications. To test the approach, we conducted a task-based evaluation with users that demonstrates its usability, and a case study that demonstrates its feasibility.This task usually includes the Entity Linking process which tries to link the named entity with a resource (reference) in a Knowledge Base (KB). a Entity Linking is also considered a way of Named Entity Disambiguation (NED), since a resource (e.g. a URI or a Wikipedia page) can determine the identity of an entity. NEE is useful in several tasks, e.g. for question answering, 1 post-processing of search results, 2,3 annotating (Web) documents. 4,5 In addition, the importance of NEE, especially for the Semantic Web, is justified by the fact that the Semantic Web realization highly depends on the availability of metadata (structured content in general) describing Web content, defined through a formal semantic structure. Thus, a major challenge for the Semantic Web is the extraction of structured data through the development of automated NEE tools.There are already several tools that support NEE, e.g. DBpedia Spotlight, 6 AlchemyAPI 7 and OpenCalais. 8 However, these tools do not allow the user/developer to easily configure them, e.g. to define their own interesting types (categories) of ent...

show abstract

Section: Lod-based Nee Tools Of General Purposementioning

confidence: 99%

Exploiting Linked Data for Open and Configurable Named Entity Extraction

Fafalios

Baritakis

Tzitzikas

2015

Int. J. Artif. Intell. Tools

View full text Add to dashboard Cite

show abstract

“…It calculates n-gram precision and a brevity penalty, and can make use of multiple reference translations as a way of capturing some of the allowable variation in translation. 4 TER calculates the number of edits required to change a hypothesis translation into a reference translation. The possible edits in TER include insertion, deletion, and substitution of single words, and an edit which moves sequences of contiguous words.…”

Section: Overviewmentioning

confidence: 99%

“…section 2); 2. Wikimeta [4]: the source sentence is analyzed by the semantic annotation platform which performs the traditional task of named entity recognition and also the task of named entity linking 5 [9]. Wikimeta proposes an approach based on a resource of contextual words called Linked Data Interface (LDI).…”

Section: Fig 1: Nerits Mashup Architecturementioning

confidence: 99%

NERITS - A Machine Translation Mashup System Using Wikimeta and DBpedia

Nebhi

Nerima

Wehrli

2013

Advanced Information Systems Engineering

View full text Add to dashboard Cite

Abstract. Recently, Machine Translation (MT) has become a quite popular technology in everyday use through Web services such as Google Translate. Although the different MT approaches provide good results, none of them exploits contextual information like Named Entity (NE) to help user comprehension. In this paper, we present NERITS, a machine translation mashup system using semantic annotation from Wikimeta and Linked Open Data (LOD) provided by DBpedia. The goal of the application is to propose a cross-lingual translation by providing detailed information extracted from DBpedia about persons, locations and organizations in the mother tongue of the user. This helps at scaling the traditional multilingual task of machine translation to cross-lingual applications.

show abstract

“…La plupart des annotateurs sémantiques actuellement disponibles établissent un lien entre une expression dans le texte et l'entité correspondante dans DBpedia. L'idée, telle que proposée par (Charton et al 2011) et (Mendes 2011, consiste en deux étapes : (1) dans un premier temps, on identifie les expressions candidates dans le texte, c'est-à-dire susceptibles d'être liées à une entité conceptuelle pertinente, et ensuite (2), on identifie, parmi toutes les entités qui pourraient être associées à une expression du texte, la plus pertinente.…”

Section: Annotation Sémantique Des Documents Numériquesunclassified

Les bibliothèques numériques sont-elles solubles dans le Web sémantique ?

Gagnon

2013

documentation

Self Cite

View full text Add to dashboard Cite

Le Web sémantique, et plus particulièrement le réseau Linked Open Data, est appelé à transformer radicalement la manière dont les bibliothèques numériques rendent accessibles leurs documents et les métadonnées sur ceux-ci. Dans cet article, après une brève présentation des principales technologies du Web sémantique, et plus particulièrement du modèle de données RDF sur lequel il repose, nous montrons comment les bibliothèques numériques peuvent s’intégrer au réseau Linked Open Data. Puis nous abordons le problème crucial de l’extraction, à partir de contenus textuels, des métadonnées nécessaires à cette intégration.The semantic Web, especially the Linked Open Data network, will radically transform the way in which digital libraries make their documents available and the metadata associated with them. Following a brief description of the principal technologies used by the semantic Web, specifically the RDF data model, the author illustrates how digital libraries can be integrated into the Linked Open Data network. He then examines the crucial problem of extracting the metadata from the textual contents in order to undertake this integration.La Web semántica y, en especial, la red Linked Open Data, tiene como objetivo transformar de forma radical la manera en que las bibliotecas digitales permiten el acceso a sus documentos y a los metadatos que se encuentran en estos documentos. En este artículo, realizamos una breve presentación de las principales tecnologías de la Web semántica, y especialmente del modelo de datos RDF, en el cual se basa. Luego, explicaremos de qué forma las bibliotecas digitales pueden integrarse en la red Linked Open Data. Finalmente, abordaremos el problema más significativo de la extracción, a partir de contenidos textuales, de los metadatos necesarios para esta integración

show abstract

Automatic Semantic Web Annotation of Named Entities

Cited by 15 publications

References 8 publications

Exploiting Linked Data for Open and Configurable Named Entity Extraction

Exploiting Linked Data for Open and Configurable Named Entity Extraction

NERITS - A Machine Translation Mashup System Using Wikimeta and DBpedia

Les bibliothèques numériques sont-elles solubles dans le Web sémantique ?

Contact Info

Product

Resources

About