First version of the Morphological Dictionary

[Konstantinos Agiannis <k [ dot ] agiannis [ at ] yandex [ dot ] com>]

Hello,

I have uploaded the first version of a Greek Morphological Dictionary. A second version will be released in July.

A link for Download is located here https://github.com/eellak/gsoc2019-greek-morpho

It contain almost 500.000 distinct forms with morphological information described according to Universal Dependencies.
It also contains Etymologies and Definitions.

Things you can do using this SQL database.

Lemmatizer table

SELECT DISTINCT form,lemma FROM words WHERE form != lemma

Lookup POS tagger (only non ambiguous POS)

SELECT DISTINCT lemma AS l,pos FROM words WHERE (SELECT count(DISTINCT pos) FROM words WHERE l = lemma) = 1;

In the current version there is a bug for Tags. In future version you will able to do

SELECT DISTINCT form FROM words WHERE tags like '%Ant%' AND gender = 'Fem';

To extract all greek female name forms.

I hope you find it useful.

Also I am looking for feedback about the next release.

Possible new features are synonyms and antonyms.

 
----
Λαμβάνετε αυτό το μήνυμα απο την λίστα: Λίστα αλληλογραφίας και συζητήσεων που απευθύνεται σε φοιτητές developers \& mentors έργων του Google Summer of Code - A discussion list for student developers and mentors of Google Summer of Code projects.,
https://lists.ellak.gr/gsoc-developers/listinfo.html

Μπορείτε να απεγγραφείτε από τη λίστα στέλνοντας κενό μήνυμα ηλ. ταχυδρομείου στη διεύθυνση <gsoc-developers+unsubscribe [ at ] ellak [ dot ] gr>.