Multilingual Document Retrieval Through Hub Languages

author: Primož Škraba, Artificial Intelligence Laboratory, Jožef Stefan Institute
published: Nov. 16, 2012,   recorded: October 2012,   views: 2692


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


In this paper we extend previous work on document retrieval across multilingual corpora. In this setting it is often assumed that we have a certain alignment given based on which we can learn mapping between spaces. In true multilingual corpora however, we often do not have alignments between all languages. There are hub languages which have alignments with many other languages. We look at the effectiveness of leveraging these alignments to learn maps which may have small or no alignments given. We test several methods and investigate the performance of various approaches on theWikipedia dataset.

See Also:

Download slides icon Download slides: is2012_skraba_hub_languages_01.pdf (1.5 MB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: