Learning Semantic Query Suggestions

Meij, Edgar; Bron, Marc; Hollink, Laura; Huurnink, Bouke; Rijke, Maarten de

doi:10.1007/978-3-642-04930-9_27

Cited by 48 publications

(32 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Work here [7][8][9][10] might show good results for query suggestion or expansion techniques. Our novel approach, however, uses an underlying ontology as a bridge for both query generation and document ranking.…”

Section: Related Workmentioning

confidence: 96%

Ontology-Supported Document Ranking for Novelty Search

Färber

2013

The Semantic Web: Semantics and Big Data

View full text Add to dashboard Cite

Abstract. Within specific domains, users generally face the challenge to populate an ontology according to their needs. Especially in case of novelty detection and forecast, the user wants to integrate novel information contained in natural text documents into his/her own ontology in order to utilise the knowledge base in a further step. In this paper, a semantic document ranking approach is proposed which serves as a prerequisite for ontology population. By using the underlying ontology for both query generation and document ranking, query and ranking are structured and, therefore, promise to provide a better ranking in terms of relevance and novelty than without using semantics.Keywords: Document ranking, Ontology-based information extraction, Novelty detection, Semantic similarity. MotivationThe existence and steady growth of the Web has granted us vast amounts of web documents in which contained information can be discovered and utilised for certain information needs. Some of the existing information extraction (IE) techniques make use of background information provided by Semantic Web ontologies. In the past, various ontology-based information extraction (OBIE) systems have been proposed, where ontologies are used within the IE process. Although there exist quite a lot of notable ontologies, in many application areas appropriate ontologies are, due to domain-specificity, too small and, hence, need to be populated in terms of adding instances and properties. For ontology population, it is a crucial task to find new textual information which is relevant to the domain expert, but has not been stored in the knowledge base (KB) and, therefore, has been made usable. In this work, we focus on the worthwhile interplay between an existing KB and a text document corpus, which -in case of the use case of trend detection -is created on demand.Within the area of ontology population, we propose a novel approach for document ranking in the context of structural search for "novel" items in text documents. We claim that semantics can be used to rank documents according to their expected novel items contained therein.

show abstract

Section: Related Workmentioning

confidence: 96%

Ontology-Supported Document Ranking for Novelty Search

Färber

2013

The Semantic Web: Semantics and Big Data

View full text Add to dashboard Cite

show abstract

“…At present, this repository includes over 11 million pages from more than 200 newspapers and periodicals published between 1618 and 1995, which adds up to over 100 million articles. xTAS includes modules for online and o ine processing, and provides essential text pre-processing modules (morphological normalisation, format and encoding reconciliation, named-entity recognition and normalisation; Meij et al, 2009). It also incorporates algorithms and tools for the identi cation of polarity (positive/support or negative/criticism), sources (opinion-holders), frequency of items, and speci c targets of discourses (Jijkoun et al, 2010).…”

Section: Wahsp Tool Featuresmentioning

confidence: 99%

A Digital Humanities Approach to the History of Culture and Science: Drugs and Eugenics Revisited in Early 20th-Century Dutch Newspapers, Using Semantic Text Mining

Snelders¹,

Huijnen²,

Verheul³

et al. 2017

CLARIN in the Low Countries

View full text Add to dashboard Cite

Human language technology developed and used in CLARIN demonstrator projects WAHSP and BILAND supports advanced forms of (multi-lingual) text mining of large datasets of newspapers. We argue that the combination of exploratory search and text mining o ers an innovative research approach to systematically set up search trails in the historical sciences. We describe the development, use, and methodological challenges of the WAHSP and BILAND text-mining tools and the successor tool, Texcavator, to support alternating forms of distant reading and close reading in newspaper collections. We will show how semantic text mining speeds up the heuristic process and thus helped to provide new and challenging perspectives on the circulation of ideas and notions regarding drugs and eugenics in Dutch newspapers in the rst four decades of the 20th century. IntroductionHistorical scholars are increasingly applying computational tools and methods to all phases of their research. Digital tools are used to open, present, and curate textual and multi-media sources in semantic text mining, for integration of geospatial information data, for various forms of visualisation, and for enhanced and multi-media publication of research results, blogs, and wikis. Digital history is a methodological approach that is framed by these digital tools' ability to make, de ne,

show abstract

“…Thus, for a specific query, RR is the reciprocal of the rank where the first correct/relevant result is given. Although this measure is mostly used in search tasks when there is only one correct answer (Kantor and Voorhees, 2000), others used it for assessing the performance of query suggestions (Meij et al, 2009;Albakour et al, 2011) as well as ranking algorithms in particular (Damljanovic et al, 2010) and IR systems (Voorhees, 1999(Voorhees, , 2003Magnini et al, 2003) in general.…”

Section: R-precision (R-prec)mentioning

confidence: 99%