Multilingual Adaptive Search for Digital Libraries

Ghorab, M. Rami; Leveling, Johannes; Lawless, Séamus; O’Connor, Alexander; Zhou, Dong; Jones, Gareth J. F.; Wade, Vincent

doi:10.1007/978-3-642-24469-8_26

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several authors have observed that the development of methodologies and tools supporting multilingual information discovery is essential to make non-English content available to end users [8], [12], [15]. Gohrab [8] proposes a framework that performs on-the-fly machine translation of queries and documents.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Enabling Multilingual Search Through Controlled Vocabularies: The AGRIS Approach

Celli¹,

Keizer²

2016

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. AGRIS is a bibliographic database of scientific publications in the food and agricultural domain. The AGRIS web portal is highly visited, reaching peaks of 350,000 visits/month from more than 200 countries and territories. Considering the variety of AGRIS users, the possibility to support crosslanguage information retrieval is crucial to improve the usefulness of the website. This paper describes a lightweight approach adopted to enable the aforementioned feature in the AGRIS system. The proposed approach relies on the adoption of a controlled vocabulary. Furthermore, we discuss how expanding user queries with synonyms increases the sensitivity of a search engine and how we can use a controlled vocabulary to achieve this result. . The former base their assertion on the evidence that keyword-based searching has become the preferred method of searching in online information systems [11]. Thus, according to them, a textual search is everything users need; there is no value in using controlled vocabularies, but free keywords are enough to help users in retrieving resources from bibliographic databases. However, several studies emphasize that many resources returned in a keyword-based search would be lost without controlled vocabularies. Gross and Taylor [10] sustain that 35.9% of results would not be found if subject headings were removed from catalog records. In fact, subject fields very often contain terms that are not available in titles and abstracts, since expert cataloguers avoid repetitions [13]. In addition to that, controlled vocabularies can mediate the implementation of advanced features, like semantic search in information retrieval systems, as in the case of the European project INSEARCH [1].

show abstract

Section: Related Workmentioning

confidence: 99%

“…Gohrab [8] proposes a framework that performs on-the-fly machine translation of queries and documents. This framework does not rely on controlled vocabularies, but supports automatic translation of queries using external services like "Google Translate 6 " or "Microsoft Translator 7 ".…”

Section: Related Workmentioning

confidence: 99%