Cross-lingual alignment and completion of Wikipedia templates

Bouma, Gosse; Duarte, Sérgio; Islam, Dewan Md Zahurul

doi:10.3115/1572433.1572437

Cited by 20 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Bouma et al [4] perform a matching of infobox attribute based on instance data. In [3] the same authors describe a system for linking the thesaurus of the Netherlands Institute for Sound and Vision to EnglishWordNet and DBpedia, using EuroWordNet, a multilingual WordNet, and Dutch Wikipedia as intermediaries for the two alignments.…”

Section: Related Workmentioning

confidence: 99%

“…4 For instance, the attributes date of birth and birth date are mapped to the ontology property dbo:birthDate 3 in the description of a person, and the attribute start is mapped to dbo: routeStart when describing a road, and to dbo:startDate when describing an event. This term normalization effort has the goal to improve properties alignment among DBpedia multilingual chapters.…”

Section: Existing Alignmentsmentioning

confidence: 99%

See 1 more Smart Citation

Filling the gaps among DBpedia multilingual chapters for question answering

Cojan

Cabrio

Gandon

2013

Proceedings of the 5th Annual ACM Web Science Conference

View full text Add to dashboard Cite

To publish information extracted from multilingual pages of Wikipedia in a structured way, the Semantic Web community has started an effort of internationalization of DBpedia. Multilingual chapters of DBpedia can in fact contain different information with respect to the English version, in particular they provide more specificity on certain topics, or fill information gaps. DBpedia multilingual chapters are well connected through instance interlinking, extracted from Wikipedia. An alignment between properties is also carried out by DBpedia contributors as a mapping from the terms used in Wikipedia to a common ontology, enabling the exploitation of information coming from the multilingual chapters of DBpedia. However, the mapping process is currently incomplete, it is time consuming since it is manually performed, and may lead to the introduction of redundant terms in the ontology, as it becomes difficult to navigate through the existing vocabulary. In this paper we propose an approach to automatically extend the existing alignments, and we integrate it in a question answering system over linked data. We report on experiments carried out applying the QAKiS (Question Answering wiKiframework-based) system on the English and French DBpedia chapters, and we show that the use of such approach broadens its coverage.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Existing Alignmentsmentioning

confidence: 99%

Filling the gaps among DBpedia multilingual chapters for question answering

Cojan

Cabrio

Gandon

2013

Proceedings of the 5th Annual ACM Web Science Conference

View full text Add to dashboard Cite

show abstract

“…Proceedings of the VLDB Endowment, Vol. 5,No. 2 Copyright 2011 VLDB Endowment 2150-8097/11/10... $ 10.00. used to derive better translations in cross-language information retrieval and machine translation [11,24,30,32].…”

Section: Introductionmentioning

confidence: 99%

“…Recognizing this problem, there are a number of ongoing e↵orts which aim to improve access to Wikipedia content. By leveraging the existing multilingual Wikipedia corpus, techniques have been proposed to: combine content provided in documents from di↵erent languages and thereby improve both documents [1,5]; find missing cross-language links [29,33]; aid in the creation of multilingual content [19]; and help users who speak di↵erent languages to search for named entities in the English Wikipedia [35].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, techniques have been proposed to identify multilingual attribute alignments for Wikipedia infoboxes. But these have important shortcomings in that they are designed for languages that share similar words [1,5], or demand a considerable amount of training data [1]. Consequently, they cannot be e↵ectively applied to languages with distinct representations or di↵erent roots; and their applicability is also limited for under-represented languages in Wikipedia, which have few pages and thus, insu cient training data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilingual schema matching for Wikipedia infoboxes

et al. 2011

View full text Add to dashboard Cite

Recent research has taken advantage of Wikipedia's multilingualism as a resource for cross-language information retrieval and machine translation, as well as proposed techniques for enriching its cross-language structure. The availability of documents in multiple languages also opens up new opportunities for querying structured Wikipedia content, and in particular, to enable answers that straddle different languages. As a step towards supporting such queries, in this paper, we propose a method for identifying mappings between attributes from infoboxes that come from pages in different languages. Our approach finds mappings in a completely automated fashion. Because it does not require training data, it is scalable: not only can it be used to find mappings between many language pairs, but it is also effective for languages that are under-represented and lack sufficient training samples. Another important benefit of our approach is that it does not depend on syntactic similarity between attribute names, and thus, it can be applied to language pairs that have distinct morphologies. We have performed an extensive experimental evaluation using a corpus consisting of pages in Portuguese, Vietnamese, and English. The results show that not only does our approach obtain high precision and recall, but it also outperforms state-of-the-art techniques. We also present a case study which demonstrates that the multilingual mappings we derive lead to substantial improvements in answer quality and coverage for structured queries over Wikipedia content.

show abstract