Relevance feedback and cross-language information retrieval
Full text is not in this repository.
Official URL: http://www.sciencedirect.com/science?_ob=ArticleUR...
This item is available in the Library Catalogue
This paper compares the use of hand translated and automatically translated documents in a relevance feedback experiment with cross linguistic information retrieval. The documents are translated by hand, and automatically, and a range of subjects is used. Subjects report that the automatic translations are poor and that they do not understand them. Despite this, the use of automatic translation from manual translation leads to indistinguishable results with relevance feedback. That is the subjects correctly report the documents are relevant or not with equal probability whether the documents are hand or machine translated, showing the immediate benefit of current AI systems.
|Research Areas:||Middlesex University Schools and Centres > School of Science and Technology > Computer Science|
Middlesex University Schools and Centres > School of Science and Technology > Computer Science > Artificial Intelligence group
|Citations on ISI Web of Science:||3|
|Deposited On:||17 Oct 2008 12:21|
|Last Modified:||28 Oct 2014 13:59|
Repository staff only: item control page
Full text downloads (NB count will be zero if no full text documents are attached to the record)
Downloads per month over the past year