Apr-28-2017, 07:53 AM
Hi everybody,
Currently, I'm looking for a ressource which contains for a noun the corresponding verb (in German!). For example: "Verständnis <=> verstanden; Schaffen <=> schaffen; Arbeit <=> arbeiten; ...".
Is there already an existing ressource, or how could I build such a file?
Since I didn't find any such ressource, I tried to write my own code to extract a list of "noun <=> corresponding verb". What I did: I took a text and looked for word in uppercase. Afterwards, I looked for words in lowercase with the additional ending "en" and if they were in the text, I got a new pair "noun <=> verb". But as you see in my example, I'm not able to extract "Verständnis <=> verstanden" and so on...so this is not really a good solution :( .
So my question is: If there doesn't already exist such a ressource; how would you extract these correspondances? I'm sure that I should work with some nltk-modules, for the lemmatization and so on...
In any case: Thanks for any help!
Currently, I'm looking for a ressource which contains for a noun the corresponding verb (in German!). For example: "Verständnis <=> verstanden; Schaffen <=> schaffen; Arbeit <=> arbeiten; ...".
Is there already an existing ressource, or how could I build such a file?
Since I didn't find any such ressource, I tried to write my own code to extract a list of "noun <=> corresponding verb". What I did: I took a text and looked for word in uppercase. Afterwards, I looked for words in lowercase with the additional ending "en" and if they were in the text, I got a new pair "noun <=> verb". But as you see in my example, I'm not able to extract "Verständnis <=> verstanden" and so on...so this is not really a good solution :( .
So my question is: If there doesn't already exist such a ressource; how would you extract these correspondances? I'm sure that I should work with some nltk-modules, for the lemmatization and so on...
In any case: Thanks for any help!