[CLARIN-Parliamentary-Records] result of Talk of Europe hands-on: different topics in original and translation text

[Laura Hollink]

Dear all, 

For those who are interested in the outcome of the last part of the Talk of Europe hands-on session: 

We started to look into the effect of languages and translation on the detected topics, but could not finish this properly. By now I have removed the typos from the queries ;) and added some documentation. Feel free to have a look and/or try it out. 

https://docs.google.com/document/d/1ddhV0a6A2satr-RsLHnoXb1K-sSV6B6995BpVljlErQ/edit?usp=sharing

If you just want to get a quick idea of the results: I have compared Dutch original speech to Spanish translation thereof and these are the top 20 topics that are most often missing in the translation:

European Commission 
exchange of information      
cooperation policy
EU programme   
application of EU law         
EU Member State
France    
appointment of staff        
competition law
EU aid          
action programme  
appointment of members
European Parliament
restriction on competition    
infringement of EU law
Committee of the Regions            
public health               
Netherlands
cooperation agreement (EU)


Best wishes,
Laura



------------------
Laura Hollink
Centrum Wiskunde & Informatica
http://homepages.cwi.nl/~hollink/





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.clarin.eu/pipermail/parliamentary-records/attachments/20170329/94b741a5/attachment.html>