Question Regarding Comparison Models

[stefanmzeidler]

Dear Repodiac,

I hope you are well. I was unable to find contact information on your profile so I am writing to you here.

I am currently working on a project for my natural language processing class on splitting German Compounds. We are trying to compare different models on accuracy and efficiency and would like to use yours. We were also wondering which models you used in the comparison you mentioned? (Would you also happen to know where we could find a version of GERTWOL?)

Kind regards,
Stefan

[repodiac]

Hi Stefan,

thank you for your message (sorry, for not having contact info here yet). I feel honored to be part of your (educational?) systematic comparison of compound splitter methods. Unfortunately, I am afraid I cannot provide you with the wanted models or methods. Back then I did a web search and played around, though wasn't satisified. That's why I came up with my "heuristic" approach using dictionaries. Haven't heard of GERTWOL, neither.

However, I'd like to know more about the results of your NLP class survey. Would appreciate it if you could provide me with a link or document :) Good speed with your survey!

[stefanmzeidler]

Thank you, @repodiac! Apologies for my late reply, we've been quite busy.

We can certainly provide you with the document when it is finished. We will only be able to compare two models due to time constraints - yours and a model called SMOR - but maybe in the future more comparisons could be done!

Kind regards,
Stefan

[repodiac]

That'd be great. Thank you. :-)