Exploiting Wikipedia and EuroWordNet to solve Cross-Lingual Question Answering

Wikipedia has become one of the ten most visited sites on the Web, and the world's leading source of Web reference information. Its rapid success has inspired hundreds of scholars from various disciplines to study its content, communication and community dynamics from various perspectives. This article presents a systematic review of scholarly research on Wikipedia. We describe our detailed, rigorous methodology for identifying over 450 scholarly studies of Wikipedia. We present the WikiLit website (http://wikilit.referata.com), where most of the papers reviewed here are described in detail. In the major section of this article, we then categorize and summarize the studies. An appendix features an extensive list of resources useful for Wikipedia researchers.

show abstract

“…Another study that examined cross-language question answering using Wikipedia (S. Ferrandez et al 2009) is covered by Medelyan et al (2009).…”

Section: Cross-language Information Retrievalmentioning

confidence: 99%

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

et al. 2012

View full text Add to dashboard Cite

show abstract

“…The method QA_complete_sentence in Algorithm 3 will return true, so there is not ellipsis resolution, because in the QA question processing (Ferrández et al, 2009)…”

Section: Algorithm 3 Ellipsis Resolution Algorithmmentioning

confidence: 99%

An authoring tool for decision support systems in context questions of ecological knowledge

Ferrández¹,

Peral²,

Gregorio³

et al. 2015

Ecological Informatics

Self Cite

View full text Add to dashboard Cite

Decision support systems (DSS) support business or organizational decision-making activities, which require the access to information that is internally stored in databases or data warehouses, and externally in the Web accessed by Information Retrieval (IR) or Question Answering (QA) systems. Graphical interfaces to query these sources of information ease to constrain dynamically query formulation based on user selections, but they present a lack of flexibility in query formulation, since the expressivity power is reduced to the user interface design. Natural language interfaces (NLI) are expected as the optimal solution. However, especially for non-expert users, a real natural communication is the most difficult to realize effectively. In this paper, we propose a NLI that improves the interaction between the user and the DSS by means of referencing previous questions or their answers (i.e. anaphora such as the pronoun reference in -What traits are affected by them?‖), or by eliding parts of the question (i.e. ellipsis such as -And to glume colour?‖ after the question -Tell me the QTLs related to awn colour in wheat‖). Moreover, in order to overcome one of the main problems of NLIs about the difficulty to adapt a NLI to a new domain, our proposal is based on ontologies that are obtained semi-automatically from a framework that allows the integration of internal and external, structured and unstructured information. Therefore, our proposal can interface with databases, data warehouses, QA and IR systems. Because of the high NL ambiguity of the resolution process, our proposal is presented as an authoring tool that helps the user to query efficiently in natural language. Finally, our proposal is tested on a DSS case scenario about Biotechnology and Agriculture, whose knowledge base is the CEREALAB database as internal structured data, and the Web (e.g. PubMed) as external unstructured information.

show abstract

“…Wikipedia is a large and valuable source of semantic information. It has been commonly pointed out in the literature that it can serve various tasks including information extraction, information retrieval, question answering systems, and ontology building [17,18]. Therefore, we choose the Wikipedia article for the term wind power [19] as our initial point and utilized this article and linked articles as the information source to facilitate the ontology building process for wind energy domain.…”

Section: Learning Ontology Concepts From the Webmentioning

confidence: 99%

Semi-automatic construction of a domain ontology for wind energy using Wikipedia articles

Küçük

Arslan

2014

Renewable Energy

View full text Add to dashboard Cite

Domain ontologies are important information sources for knowledge-based systems. Yet, building domain ontologies from scratch is known to be a very labor-intensive process. In this study, we present our semi-automatic approach to building an ontology for the domain of wind energy which is an important type of renewable energy with a growing share in electricity generation all over the world. Related Wikipedia articles are first processed in an automated manner to determine the basic concepts of the domain together with their properties and next the concepts, properties, and relationships are organized to arrive at the ultimate ontology. We also provide pointers to other engineering ontologies which could be utilized together with the proposed wind energy ontology in addition to its prospective application areas. The current study is significant as, to the best of our knowledge, it proposes the first considerably wide-coverage ontology for the wind energy domain and the ontology is built through a semi-automatic process which makes use of the related Web resources, thereby reducing the overall cost of the ontology building process.

show abstract

Exploiting Wikipedia and EuroWordNet to solve Cross-Lingual Question Answering

Cited by 26 publications

References 44 publications

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

An authoring tool for decision support systems in context questions of ecological knowledge

Semi-automatic construction of a domain ontology for wind energy using Wikipedia articles

Contact Info

Product

Resources

About