Exploiting the Web as the multilingual corpus for unknown query translation

Abstract

Users' cross-lingual queries to a digital library system might be short and the query terms may not be included in a common translation dictionary (unknown terms). In this article, the authors investigate the feasibility of exploiting the Web as the multilingual corpus source to translate unknown query terms for cross-language information retrieval in digital libraries. They propose a Webbased term translation approach to determine effective translations for unknown query terms by mining bilingual search-result pages obtained from a real Web search engine. This approach can enhance the construction of a domain-specific bilingual lexicon and bring multilingual support to a digital library that only has monolingual document collections. Very promising results have been obtained in generating effective translation equivalents for many unknown terms, including proper nouns, technical terms, and Web query terms, and in assisting bilingual lexicon construction for a real digital library system.

Web log analysis: a review of a decade of studies about information acquisition, inspection and interpretation of user interaction

“…There are many applications on the World-Wide Web that make use of this multilingual approach (Gao et al 2007;Wang et al 2006;Hu et al 2008). In this context, query suggestion and expansion is performed between different languages too.…”

“…In Wang et al (2006) a Web-based approach for dealing with the translation of unknown query terms for cross-language information retrieval is presented. With the proposed term extraction and term translation methods, it is feasible to translate unknown terms and construct a bilingual lexicon for key terms extracted from documents.…”

A delimiter‐based general approach for Chinese term extraction

“…The first are rule-based methods that rely on lexical analysis and syntactic analysis to extract named entities from documents. The second are statisticsbased methods that extract lexical patterns with statistical significance (Wang, Teng, Lu, & Chien, 2006). Because rulebased approaches rely on predefined linguistic patterns that require training and are not so easily applied to different domains, this section mainly focuses on the statistics-based approaches.…”

Precision at K in Multilingual Information Retrieval

“…Language wise performance is not measured at K positions. Precision at top K documents of MLIR is measured using equation (2). This proposed metric is useful for understanding the retrieval effectiveness of multiple document languages.…”

“…Our work has used first type of data collection to measure the proposed metric. The MLIR techniques are: An approach for exploiting the Web as the multilingual corpus source for translating unknown query terms have been proposed by [2]. Many user queries contain terms not found in an ordinary translation dictionary.…”