dasem
dasem copied to clipboard
fnielsen
Danish Semantic analysis
Hi, I'm having problems with retsinformation.py - are there any other requirements than those in the readme and requirements.txt?
I have gotten W2V with the package to work with the Gutenberg corpus, but I am having trouble getting other corpora to work. I have downloaded the corpora as per...
``` File "/usr/lib/python2.7/tarfile.py", line 1691, in open return func(name, filemode, fileobj, **kwargs) File "/usr/lib/python2.7/tarfile.py", line 1749, in gzopen raise ReadError("not a gzip file") tarfile.ReadError: not a gzip file ```
Something is wrong with eparole unpacking. The filename and filename of the unpacked has perhaps changed?
Extend decompounder with - [ ] machine learning on ngrams - [ ] dictionary-based splitting