A Machine Learning Approach to Multilingual and Cross-Lingual Ontology Matching

Spohr, Dennis; Hollink, Laura; Cimiano, Philipp

doi:10.1007/978-3-642-25073-6_42

Cited by 60 publications

(45 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It seems plausible to assume that current techniques can be extended to support multiple languages without requiring the development of radically different approaches. In fact, most of the extant current ontology matching systems rely to some extent on comparisons based on lexical information and could be extended by allowing for crosslanguage comparisons by either integrating machine translation systems (compare [17,39,35]) or multilingual lexical resources. Other matching systems rely on the computation of semantic similarity or relatedness between entities.…”

Section: Figure 2 Example Of Cross-lingual Linguistic Mappings Mediamentioning

confidence: 99%

Challenges for the multilingual Web of Data

Gracia

Montiel-Ponsoda

Cimiano

et al. 2012

Journal of Web Semantics

Self Cite

View full text Add to dashboard Cite

The Web has witnessed an enormous growth in the amount of semantic information published in recent years. This growth has been stimulated to a large extent by the emergence of Linked Data. Although this brings us a big step closer to the vision of a Semantic Web, it also raises new issues such as the need for dealing with information expressed in different natural languages. Indeed, although the Web of Data can contain any kind of information in any language, it still lacks explicit mechanisms to automatically reconcile such information when it is expressed in different languages. This leads to situations in which data expressed in a certain language is not easily accessible to speakers of other languages.The Web of Data shows the potential for being extended to a truly multilingual web as vocabularies and data can be published in a language-independent fashion, while associated language-dependent (linguistic) information supporting the access across languages can be stored separately. In this sense, the multilingual Web of Data can be realized in our view as a layer of services and resources on top of the existing Linked Data infrastructure adding i) linguistic information for data and vocabularies in different languages, ii) mappings between data with labels in different languages, and iii) services to dynamically access and traverse Linked Data across different languages.In this article we present this vision of a multilingual Web of Data. We discuss challenges that need to be addressed to make this vision come true and discuss the role that techniques such as ontology localization, ontology mapping, and cross-lingual ontology-based information access and presentation will play in achieving this. Further, we propose an initial architecture and describe a roadmap that can provide a basis for the implementation of this vision.

show abstract

Section: Figure 2 Example Of Cross-lingual Linguistic Mappings Mediamentioning

confidence: 99%

Challenges for the multilingual Web of Data

Gracia

Montiel-Ponsoda

Cimiano

et al. 2012

Journal of Web Semantics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ontology localization [12] of an adapting culture context of data. Online avatar uses speech of recording and 3DSMax, Maya to improve flexibility and effectiveness.…”

Section: B Methodsmentioning

confidence: 99%

Evaluation of multilingual websites using localization matrix

Katkade¹,

Katti²,

Dhutadmal³

2017

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-Creating, implementing and maintaining a huge website can be a terrifying task when the website is within multiple natural languages. The probable communication issues related to website content and structure become even more complex for multi-linguistic sites. The fact is that a majority of Web consumers today don't speak English, and they opt to access websites about companies' services in their own language. Organizations always want to keep a global image for that it required to use the website localization for local users. People can communicate via multilingual websites which need to browse independent screens for each one. It brings one of the most crucial areas exposed up by the period of electronic procedure. Web page localization is a solution to many organizations are leverage to appropriately translate their websites so their international customers can read site content and access information in their native languages. This address to improve culturally adaption of any multi-lingual website that focuses individual user-centric.

show abstract

“…Spohr et al [4] present an approach applying ML techniques. They use a small amount of manually produced cross-lingual alignments in order to learn a matching function for two cross-lingual ontologies.…”

Section: Cross-lingual Ontology Matchingmentioning

confidence: 99%

“…Cross-lingual data and ontology matching is therefore a crucial task in order to foster the creation of a global information network, instead of a set of linguistically isolated data islands. However, as observed by Spohr et al [4], most of the ontology alignment algorithms assume that the ontologies to be aligned are defined in a single natural language.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Light-Weight Cross-Lingual Ontology Matching with LYAM++

Tigrine

Bellahsène

Todorov

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. During the last decade, several automatic ontology matching systems were developed to address the problem of ontology heterogeneity. Aligning cross-lingual ontologies is among the current challenging issues in the field of ontology matching. The majority of the existing approaches rely on machine translation to deal with this problem. However, inherent problems of machine translation are imprecision and ambiguity. In this paper, we propose a novel approach to the cross-lingual ontology matching task, relying on the large multilingual semantic network BabelNet as a source of background knowledge to assist the matching process. We have designed and tested a novel orchestration of the components of the matching workflow. Our approach is implemented under the form of a prototype named LYAM++ (Yet Another Matcher-Light)-a fully automatic cross-lingual ontology matching system that does not rely on machine translation. We report the results of our experiments that show that LYAM++ outperforms considerably the best techniques in the state-of-the-art according to the obtained results on the MultiFarm datasets of the Ontology Alignment Evaluation Initiative 2014.

show abstract

A Machine Learning Approach to Multilingual and Cross-Lingual Ontology Matching

Cited by 60 publications

References 7 publications

Challenges for the multilingual Web of Data

Challenges for the multilingual Web of Data

Evaluation of multilingual websites using localization matrix

Light-Weight Cross-Lingual Ontology Matching with LYAM++

Contact Info

Product

Resources

About