Exploiting the category structure of Wikipedia for entity ranking

Kaptein, Rianne; Kamps, Jaap

doi:10.1016/j.artint.2012.06.003

Cited by 42 publications

(41 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Broadly similar in spirit to our WikiSDM approach, additional structured content from Wikipedia such as links can be also used to perform document retrieval [32,10]. Wikipedia entities and their categories, in turn, can be used to improve INEX-style entity retrieval [26]. In our work, we also use Wikipedia to define our vocabulary of entities and develop models to rank these entities for keyword queries.…”

Section: Related Workmentioning

confidence: 99%

“…One of the methods closest to ours is the work of Kaptein and Kamps [26], who also address the problem of retrieving entities for web queries. They assume the availability of type information, either as an explicit category (given by the user) or a latent one that needs to be extracted from the query.…”

Section: Related Workmentioning

confidence: 99%

“…This baseline is closest in spirit to INEX-like entity retrieval from Wikipedia [26] and is the alternative to our approach of issuing the query against a document retrieval system and then …”

Section: Wikipedia Fulltext Index (Wikisdm)mentioning

confidence: 99%

See 2 more Smart Citations

Ranking Entities for Web Queries Through Text and Knowledge

Schuhmacher

Dietz

Ponzetto

2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

When humans explain complex topics, they naturally talk about involved entities, such as people, locations, or events. In this paper, we aim at automating this process by retrieving and ranking entities that are relevant to understand free-text web-style queries like Argentine British relations, which typically demand a set of heterogeneous entities with no specific target type like, for instance, Falklands_-War or Margaret_Thatcher, as answer. Standard approaches to entity retrieval rely purely on features from the knowledge base. We approach the problem from the opposite direction, namely by analyzing web documents that are found to be query-relevant. Our approach hinges on entity linking technology that identifies entity mentions and links them to a knowledge base like Wikipedia. We use a learning-to-rank approach and study different features that use documents, entity mentions, and knowledge base entities -thus bridging document and entity retrieval. Since established benchmarks for this problem do not exist, we use TREC test collections for document ranking and collect custom relevance judgments for entities. Experiments on TREC Robust04 and TREC Web13/14 data show that: i) single entity features, like the frequency of occurrence within the top-ranked documents, or the query retrieval score against a knowledge base, perform generally well; ii) the best overall performance is achieved when combining different features that relate an entity to the query, its document mentions, and its knowledge base representation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Ranking Entities for Web Queries Through Text and Knowledge

Schuhmacher

Dietz

Ponzetto

2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Examples include information retrieval [4,14,18], named entity disambiguation [1,2,7,8,11,12], text classification [25] and entity ranking [10]. To extract the content of an entity context, many researches directly used the Wikipedia article describing the entity [1,2,8,9,14,[25][26][27]; some works extended the article with all the other Wikipedia articles linked to the Wikipedia article describing the entity [6,7,12]; while some only considered the first paragraph of the Wikipedia article describing the entity [2].…”

Section: Related Workmentioning

confidence: 99%

What’s New? Analysing Language-Specific Wikipedia Entity Contexts to Support Entity-Centric News Retrieval

Zhou

Demidova

Cristea

2017

Transactions on Computational Collective Intelligence XXVI

View full text Add to dashboard Cite

“…Wikipedia uses categories to classify articles in a huge pseudo-taxonomy, which has also been collaboratively created (Muchnik et al, 2007;Thornton;McDonald, 2012;Kaptein;Kamps, 2013). Although the quality of content in Wikipedia pages is comparable to other encyclopedias (Lih, 2004), this cannot be said about the taxonomy of categories used to describe its content (Silva et al, 2011;Salah et al, 2012;Hejazy;El-Beltagy, 2013 (2008) showed that Wikipedia coverage depended on its users' interests, as well the category system used to organize them.…”

Section: Introductionmentioning

confidence: 99%

Semi-automatic generation of a corpus of Wikipedia articles on science and technology

Minguillón¹,

Lerga²,

Aibar³

et al. 2017

EPI

View full text Add to dashboard Cite

Eduard Aibar is an associate professor of Science and Technology Studies at the Arts & Humanities Department, Universitat Oberta de Catalunya (UOC). He has been the director of the Internet Interdisciplinary Institute and vice-president for research at UOC. He leads a research group on open science and innovation. His research has focused on the interaction between scientific and technological development and organizational and social change in areas such as eGovernment, town planning, and the Internet. He is currently leading a research project on the relationship between science and peer production. AbstractDespite the huge amount of scientific and technological content available on the World Wide Web, most of it is closed behind paywalls, as with academic journals, or almost invisible, as with institutional repositories. Wikipedia can act as a chain-transfer agent, providing people with an accessible, organized structure containing both understandable content and links to original sources. In Wikipedia, categories are collaboratively created and thus become a folksonomy rather than a true taxonomy. Consequently, categories are not a reliable tool to identify topics' organization. In this paper we describe a semi-automatic method, based on random walks, for determining a subset of pages containing scientific and technological content in the Spanish Wikipedia. Using the Unesco taxonomy, we determined the underlying graph structure of our corpus and detected clusters of pages strongly linked, establishing relationships between knowledge domains. Finally, we present the distribution of Wikipedia articles according to the Unesco taxonomy and the resulting map of scientific and technological content. KeywordsWikipedia; Science and technology; Corpus; Infomap; Community detection; Unesco taxonomy. ResumenA pesar de la gran cantidad de contenido científico y tecnológico disponible en la World Wide Web, su mayoría se encuentra encerrado tras sistemas de pago, como las revistas académicas, o es casi invisible, como los repositorios institucionales. Wikipedia puede actuar como un agente de transferencia, proporcionando una estructura organizada y accesible conteniendo tanto contenidos como enlaces a las fuentes originales. En Wikipedia las categorías se han cread colaborativamente y por lo tanto son más una folksonomía que una verdadera taxonomía. Consecuentemente, las categorías no son una herramienta válida para identificar la organización de los contenidos. En este artículo se describe un método semi-automático, basado en paseos aleatorios, para determinar un subconjunto de páginas con contenido científico y tecnológico de la Wikipedia españo-la. Usando la taxonomía Unesco, se determina la estructura subyacente del grafo del corpus y se detectan grupos de páginas fuertemente enlazadas, estableciendo las relaciones entre las áreas de conocimiento. Finalmente, se presenta la distribución de artículos de Wikipedia de acuerdo con la taxonomía Unesco y el mapa resultante de contenido científico y tecnológico.

show abstract

Exploiting the category structure of Wikipedia for entity ranking

Cited by 42 publications

References 8 publications

Ranking Entities for Web Queries Through Text and Knowledge

Ranking Entities for Web Queries Through Text and Knowledge

What’s New? Analysing Language-Specific Wikipedia Entity Contexts to Support Entity-Centric News Retrieval

Semi-automatic generation of a corpus of Wikipedia articles on science and technology

Contact Info

Product

Resources

About