An Intelligent Search Infrastructure for Language Resources on the Web

Abstract

Language occupies a central role on the web: most content is expressed in language, and most access takes place via natural language search. Today, investigation of human language depends on access to this vast store of language data. This project will develop new infrastructure for accessing language resources, namely a language-aware search engine. Language technologies will be employed to classify web content, and a special search keyword 'lang:' will constrain search results to be in the specified language. The system will be integrated with major language archives in Australia and overseas, and deployed on the high performance computing infrastructure at Melbourne University's Advanced ..

Related publications (2)

Open source corpus analysis tools for Malay

T Baldwin, S Awab

2006-01-01

Tokenisers, lemmatisers and POS taggers are vital to the linguistic and digital furtherment of any language. In this paper, we pre..

Reconsidering language identification for written language resources

B Hughes, T Baldwin, S Bird, J Nicholson, A MacKinlay

2006-01-01

The task of identifying the language in which a given document (ranging from a sentence to thousands of pages) is written has been..