Darreri lu Sipariu

dû Tradutturi Sicilianu

tokenization:

mi% 20piaci% 20jucari% 20cu% 20la% 20gatta .

subwords:

mi@@ % 20@@ piaci@@ % 20@@ juc@@ ari@@ % 20@@ cu@@ % 20@@ la@@ % 20@@ g@@ atta .

0.709 Mi% 20% 20% 20% 20% 20% of 20cat.
0.731 Mi% 20% 20% 20% 20% 20% suitable.
0.792 Mi% 20% 20% 20% 20% 20% sub 20cat.
0.793 Mi% 20% 20% 20% 20% 20% are 20cat.
0.911 Mi% 20% 20% 20% 20% 20% suitable 20s.

urtimu agg.: 2023.05.20

Back here, "behind the curtain," you can see how the Sicilian Translator works.

First, it tokenizes the input sentence to a reduced form. Then subword splitting breaks the words into shorter units, which are then passed to the translator.

The translator returns the Top 5 translations of the input sentence, which this page displays in detokenized form along with the translation score. Like golf, a lower score is a better score.

For more information, please see the documentation and the Sicilian NLP pages.